Triple
T2160126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Libreville |
E47980
|
entity |
| Predicate | languageSpoken |
P151
|
FINISHED |
| Object | Fang |
E56340
|
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: Fang | Statement: [Libreville, languageSpoken, Fang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fang Context triple: [Libreville, languageSpoken, Fang]
-
A.
Fang
chosen
Fang is a Bantu language widely spoken by the Fang people of Central Africa, particularly in Equatorial Guinea, Gabon, and Cameroon.
-
B.
Fumei
Fumei is a given name most notably borne by Mao Fumei, the first wife of Chinese leader Chiang Kai-shek.
-
C.
Flen
Flen is a small Swedish town known as the administrative center of Flen Municipality in the province of Södermanland.
-
D.
Quatchi
Quatchi is a sasquatch character who served as one of the official mascots of the 2010 Winter Olympics in Vancouver.
-
E.
Shenwa
Shenwa is a Zenati Berber language spoken by a small community in the Chenoua (Shenwa) region of 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_69a88a1d1fd8819088b34990d69a712f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe8894d481908eda9363fd36fea6 |
completed | March 7, 2026, 5:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae58e9ceb08190871ff9c57ece23c0 |
completed | March 9, 2026, 5:21 a.m. |
Created at: March 4, 2026, 7:45 p.m.