Triple
T8434518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghoubbet al-Kharab |
E199192
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Tadjoura |
E38891
|
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: Tadjoura | Statement: [Ghoubbet al-Kharab, near, Tadjoura]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tadjoura Context triple: [Ghoubbet al-Kharab, near, Tadjoura]
-
A.
Tadjoura
chosen
Tadjoura is a historic coastal town in Djibouti on the Gulf of Tadjoura, known as one of the country’s oldest settlements and a traditional trading hub.
-
B.
Mopti
Mopti is a major city in central Mali known as a bustling river port and commercial hub situated at the confluence of the Niger and Bani rivers.
-
C.
Dzaoudzi
Dzaoudzi is a coastal town on the island of Petite-Terre in Mayotte, serving as one of the territory’s main urban centers and former capital.
-
D.
Kousséri
Kousséri is a town in northern Cameroon located on the Logone River, serving as a key border crossing and commercial link with N'Djamena, the capital of Chad.
-
E.
Bordj Okhriss
Bordj Okhriss is a town and commune located in Bouira Province in northern Algeria.
- 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_69ca8314cd6c8190a6b8c2a1096e18f3 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbd1a905ac8190b1015e1da9b16938 |
completed | March 31, 2026, 1:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce399e8efc8190ad6fa8a6cf91797c |
completed | April 2, 2026, 9:40 a.m. |
Created at: March 30, 2026, 6:07 p.m.