Triple
T14098996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agatu |
E339329
|
entity |
| Predicate | borders |
P224
|
FINISHED |
| Object | Apa |
E338086
|
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: Apa | Statement: [Agatu, borders, Apa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Apa Context triple: [Agatu, borders, Apa]
-
A.
Apa
chosen
Apa is a local government area in Benue State, Nigeria, traditionally inhabited by the Idoma people.
-
B.
Apoi
Apoi is an ethnic group in southwestern Nigeria closely related to and located near the Ilaje people.
-
C.
Ang
Ang is a casual nickname commonly used for the given name Angela.
-
D.
Parea
Parea is a small coastal village on the island of Huahine in French Polynesia, known for its tranquil beaches and traditional Polynesian atmosphere.
-
E.
Akapana
Akapana is a monumental terraced pyramid and ceremonial complex at the ancient city of Tiwanaku, serving as one of the most important religious and political centers of the Middle Horizon Andes.
- 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_69d81c69b5c8819094aa1abf18302908 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5fba7c10819095b1299b7b4f0310 |
completed | April 14, 2026, 3:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0adfc28819097a1bfd56739c286 |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:22 p.m.