Triple
T18658718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tabarka |
E456133
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object |
Aïn Draham
Aïn Draham is a mountainous town in northwestern Tunisia known for its dense cork oak forests, cool rainy climate, and role as a popular nature and ecotourism destination.
|
E1336907
|
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: Aïn Draham | Statement: [Tabarka, nearbyCity, Aïn Draham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aïn Draham Context triple: [Tabarka, nearbyCity, Aïn Draham]
-
A.
Aïn Laloui
Aïn Laloui is a town and commune located in northern Algeria’s Bouira Province.
-
B.
Aïn Fakroun
Aïn Fakroun is a town and commune in northeastern Algeria known as a local administrative and commercial center within Oum El Bouaghi Province.
-
C.
Aïn El Turk
Aïn El Turk is a coastal town and popular Mediterranean beach resort in northwestern Algeria, near the city of Oran.
-
D.
M'Ress
M'Ress is a feline-like Caitian Starfleet communications officer who appears as a recurring character in Star Trek: The Animated Series.
-
E.
Aïn Beïda
Aïn Beïda is a city in northeastern Algeria known as a regional commercial and administrative center with historical roots dating back to the Ottoman period.
- 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: Aïn Draham Triple: [Tabarka, nearbyCity, Aïn Draham]
Generated description
Aïn Draham is a mountainous town in northwestern Tunisia known for its dense cork oak forests, cool rainy climate, and role as a popular nature and ecotourism destination.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Aïn Draham Target entity description: Aïn Draham is a mountainous town in northwestern Tunisia known for its dense cork oak forests, cool rainy climate, and role as a popular nature and ecotourism destination.
-
A.
Aïn Laloui
Aïn Laloui is a town and commune located in northern Algeria’s Bouira Province.
-
B.
Aïn Fakroun
Aïn Fakroun is a town and commune in northeastern Algeria known as a local administrative and commercial center within Oum El Bouaghi Province.
-
C.
Aïn El Turk
Aïn El Turk is a coastal town and popular Mediterranean beach resort in northwestern Algeria, near the city of Oran.
-
D.
M'Ress
M'Ress is a feline-like Caitian Starfleet communications officer who appears as a recurring character in Star Trek: The Animated Series.
-
E.
Aïn Beïda
Aïn Beïda is a city in northeastern Algeria known as a regional commercial and administrative center with historical roots dating back to the Ottoman period.
- 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_69d8d38ea1e88190997e9b231190ba6f |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e55087ae8081909cb4c0ce6c809d55 |
completed | April 19, 2026, 10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05234a2dec81909bab45814c9f2ac2 |
completed | May 14, 2026, 1:20 a.m. |
| NEDg | Description generation | batch_6a0524f7212c81909389930234db24df |
completed | May 14, 2026, 1:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0525460ce88190bdfa6e82507a7c3b |
completed | May 14, 2026, 1:28 a.m. |
Created at: April 10, 2026, 11:48 a.m.