Triple
T4101390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Djerba |
E87947
|
entity |
| Predicate | hasVillage |
P4011
|
FINISHED |
| Object |
Guellala
Guellala is a traditional pottery-making village on the Tunisian island of Djerba, known for its distinctive ceramics and cultural heritage.
|
E450483
|
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: Guellala | Statement: [Djerba, hasVillage, Guellala]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Guellala Context triple: [Djerba, hasVillage, Guellala]
-
A.
Boulemane
Boulemane is a town and province in northeastern Morocco known for its mountainous landscapes and location within the Middle Atlas region.
-
B.
Zouerate
Zouerate is an iron-mining town in northern Mauritania that has served as an important industrial center and historical focal point in the Western Sahara conflict.
-
C.
Taounate
Taounate is a prominent city in northern Morocco known as an administrative and commercial center for the surrounding rural and mountainous region.
-
D.
Chenoua
Chenoua is a Berber (Amazigh) language variety spoken by the Chenoua people in northern Algeria.
-
E.
Aït Melloul
Aït Melloul is a town in southwestern Morocco that forms part of the greater Agadir metropolitan area and serves as an important local commercial and residential hub.
- 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: Guellala Triple: [Djerba, hasVillage, Guellala]
Generated description
Guellala is a traditional pottery-making village on the Tunisian island of Djerba, known for its distinctive ceramics and cultural heritage.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Guellala Target entity description: Guellala is a traditional pottery-making village on the Tunisian island of Djerba, known for its distinctive ceramics and cultural heritage.
-
A.
Boulemane
Boulemane is a town and province in northeastern Morocco known for its mountainous landscapes and location within the Middle Atlas region.
-
B.
Zouerate
Zouerate is an iron-mining town in northern Mauritania that has served as an important industrial center and historical focal point in the Western Sahara conflict.
-
C.
Taounate
Taounate is a prominent city in northern Morocco known as an administrative and commercial center for the surrounding rural and mountainous region.
-
D.
Chenoua
Chenoua is a Berber (Amazigh) language variety spoken by the Chenoua people in northern Algeria.
-
E.
Aït Melloul
Aït Melloul is a town in southwestern Morocco that forms part of the greater Agadir metropolitan area and serves as an important local commercial and residential hub.
- 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_69aed94564cc8190a9c1457daedb6e7f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0ed168819093c83ba079d6725c |
completed | March 9, 2026, 5:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdacc411808190a80e0d6355c1cc60 |
completed | March 20, 2026, 8:23 p.m. |
| NEDg | Description generation | batch_69bdb13e7d188190b17b416bb37846a3 |
completed | March 20, 2026, 8:42 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bdb1a061448190915d0323efe5d992 |
completed | March 20, 2026, 8:44 p.m. |
Created at: March 9, 2026, 3:40 p.m.