Triple
T4101365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Djerba |
E87947
|
entity |
| Predicate | hasCapital |
P204
|
FINISHED |
| Object | Houmt Souk |
E317117
|
NE FINISHED |
How this triple was built (2 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: Houmt Souk | Statement: [Djerba, hasCapital, Houmt Souk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Houmt Souk Context triple: [Djerba, hasCapital, Houmt Souk]
-
A.
Houmt Souk
chosen
Houmt Souk is the main town of the Tunisian island of Djerba, known for its traditional markets, whitewashed architecture, and historic role as a Mediterranean trading hub.
-
B.
Sousse
Sousse is a major coastal city in eastern Tunisia known for its historic medina, tourism, and role in the country’s modern political events.
-
C.
Nouaceur
Nouaceur is a town and municipality in the Casablanca-Settat region of Morocco, known for hosting Mohammed V International Airport.
-
D.
Hammamet
Hammamet is a popular Tunisian coastal resort town on the Mediterranean Sea, known for its beaches, tourism, and historic medina.
-
E.
Souk El Had
Souk El Had is a large traditional market in Agadir, Morocco, known for its wide variety of local goods, produce, crafts, and textiles.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69b5960443c48190901c674d2e947cef |
completed | March 14, 2026, 5:08 p.m. |
Created at: March 9, 2026, 3:40 p.m.