Triple
T23224493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sirsukh |
E580978
|
entity |
| Predicate | includedIn |
P1393
|
FINISHED |
| Object |
UNESCO World Heritage Site "Taxila"
Taxila is an ancient archaeological complex in Pakistan that was a major center of Gandharan civilization and Buddhist learning, now recognized as a UNESCO World Heritage Site.
|
E912479
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: UNESCO World Heritage Site "Taxila" | Statement: [Sirsukh, includedIn, UNESCO World Heritage Site "Taxila"]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UNESCO World Heritage Site "Taxila" Context triple: [Sirsukh, includedIn, UNESCO World Heritage Site "Taxila"]
-
A.
UNESCO World Heritage Site buffer zone (Taxila)
The UNESCO World Heritage Site buffer zone (Taxila) is a protected area surrounding the core archaeological remains of ancient Taxila, established to safeguard its cultural heritage and landscape from encroachment and inappropriate development.
-
B.
Takht-i-Bahi
Takht-i-Bahi is a well-preserved ancient Buddhist monastic complex and UNESCO World Heritage Site in northwestern Pakistan, renowned for its Gandharan architecture and archaeological significance.
-
C.
Taxila Museum
Taxila Museum is an archaeological museum in Pakistan renowned for its extensive collection of Gandharan art and artifacts excavated from the ancient city of Taxila and its surrounding sites.
-
D.
Historical Monuments of Thatta
The Historical Monuments of Thatta are a UNESCO World Heritage ensemble in Sindh, Pakistan, renowned for their grand Mughal-era necropolis, intricate stone carvings, and richly decorated tombs that reflect a fusion of Islamic and local architectural traditions.
-
E.
Old Kandahar archaeological site
Old Kandahar archaeological site is an ancient urban center in southern Afghanistan, widely regarded as the location of Alexandria in Arachosia founded by Alexander the Great.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: UNESCO World Heritage Site "Taxila" Triple: [Sirsukh, includedIn, UNESCO World Heritage Site "Taxila"]
Generated description
Taxila is an ancient archaeological complex in Pakistan that was a major center of Gandharan civilization and Buddhist learning, now recognized as a UNESCO World Heritage Site.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: UNESCO World Heritage Site "Taxila" Target entity description: Taxila is an ancient archaeological complex in Pakistan that was a major center of Gandharan civilization and Buddhist learning, now recognized as a UNESCO World Heritage Site.
-
A.
UNESCO World Heritage Site buffer zone (Taxila)
chosen
The UNESCO World Heritage Site buffer zone (Taxila) is a protected area surrounding the core archaeological remains of ancient Taxila, established to safeguard its cultural heritage and landscape from encroachment and inappropriate development.
-
B.
Takht-i-Bahi
Takht-i-Bahi is a well-preserved ancient Buddhist monastic complex and UNESCO World Heritage Site in northwestern Pakistan, renowned for its Gandharan architecture and archaeological significance.
-
C.
Taxila Museum
Taxila Museum is an archaeological museum in Pakistan renowned for its extensive collection of Gandharan art and artifacts excavated from the ancient city of Taxila and its surrounding sites.
-
D.
Historical Monuments of Thatta
The Historical Monuments of Thatta are a UNESCO World Heritage ensemble in Sindh, Pakistan, renowned for their grand Mughal-era necropolis, intricate stone carvings, and richly decorated tombs that reflect a fusion of Islamic and local architectural traditions.
-
E.
Old Kandahar archaeological site
Old Kandahar archaeological site is an ancient urban center in southern Afghanistan, widely regarded as the location of Alexandria in Arachosia founded by Alexander the Great.
- F. None of above.
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f1922d30b08190a3c54bab58f5c8e7 |
completed | April 29, 2026, 5:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c5db5ec208190a3bd9405d42a7424 |
completed | May 19, 2026, 12:55 p.m. |
| NEDg | Description generation | batch_6a0c5eca0b688190b868c58dfe1e3cee |
completed | May 19, 2026, 12:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c5f2c4dfc819094be3721253e8f11 |
completed | May 19, 2026, 1:01 p.m. |
Created at: April 17, 2026, 4:08 p.m.