Triple
T19595749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | siege of Lanka (Longka) |
E470343
|
entity |
| Predicate | hasSetting |
P3538
|
FINISHED |
| Object |
Longka
Longka is the legendary island fortress city ruled by the demon king Ravana in the Hindu epic Ramayana.
|
E1385354
|
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: Longka | Statement: [siege of Lanka (Longka), hasSetting, Longka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Longka Context triple: [siege of Lanka (Longka), hasSetting, Longka]
-
A.
TNT Express
TNT Express is an international courier and logistics company known for its global parcel delivery and express mail services.
-
B.
Coupang
Coupang is a South Korean e-commerce company often called the “Amazon of Korea,” known for its ultra-fast delivery service and dominant online retail platform.
-
C.
Channel Express
Channel Express was a British airline that operated cargo and passenger services before rebranding and evolving into the low-cost carrier Jet2.com.
-
D.
DHL
DHL is a global logistics and courier company known for its international express mail, freight transportation, and supply chain management services.
-
E.
DHL
DHL is the Dag Hammarskjöld Library, the United Nations’ main research and information resource center located at its headquarters in New York.
- 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: Longka Triple: [siege of Lanka (Longka), hasSetting, Longka]
Generated description
Longka is the legendary island fortress city ruled by the demon king Ravana in the Hindu epic Ramayana.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Longka Target entity description: Longka is the legendary island fortress city ruled by the demon king Ravana in the Hindu epic Ramayana.
-
A.
TNT Express
TNT Express is an international courier and logistics company known for its global parcel delivery and express mail services.
-
B.
Coupang
Coupang is a South Korean e-commerce company often called the “Amazon of Korea,” known for its ultra-fast delivery service and dominant online retail platform.
-
C.
Channel Express
Channel Express was a British airline that operated cargo and passenger services before rebranding and evolving into the low-cost carrier Jet2.com.
-
D.
DHL
DHL is a global logistics and courier company known for its international express mail, freight transportation, and supply chain management services.
-
E.
DHL
DHL is the Dag Hammarskjöld Library, the United Nations’ main research and information resource center located at its headquarters in New York.
- F. None of above. chosen
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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e6407a09608190aa1df92f8c21f9e7 |
completed | April 20, 2026, 3:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a075f1926b88190870d13afa412b444 |
completed | May 15, 2026, 5:59 p.m. |
| NEDg | Description generation | batch_6a076110cebc8190b3d7be3e858c92bf |
completed | May 15, 2026, 6:08 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07616ce66881909846d54ca6e2ca99 |
completed | May 15, 2026, 6:09 p.m. |
Created at: April 10, 2026, 1:43 p.m.