Triple
T3982156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annobonese people |
E85782
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Fá d’Ambô |
E182804
|
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: Fá d’Ambô | Statement: [Annobonese people, language, Fá d’Ambô]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fá d’Ambô Context triple: [Annobonese people, language, Fá d’Ambô]
-
A.
Fa d’Ambô
chosen
Fa d’Ambô is a Portuguese-based creole language spoken primarily on the island of Annobón in Equatorial Guinea.
-
B.
Follaz
Follaz is a tributary stream of the Dranse river in the Alpine region of eastern France.
-
C.
Ambiko
Ambiko is a small settlement in Ethiopia located near Ras Dashen, the country’s highest mountain in the Simien Mountains range.
-
D.
Farkadona
Farkadona is a town and municipality in central Greece, situated in the Thessaly region.
-
E.
Ambo
Ambo is a coastal village on Tarawa Atoll in Kiribati, known for its role as a small residential and administrative community in the central Pacific.
- 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_69aed93908348190a26c8aaf4fab3e86 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef9db804c8190ad96656cb7b1a4fe |
completed | March 9, 2026, 4:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b540257c188190899b00bf1d0247d2 |
completed | March 14, 2026, 11:01 a.m. |
Created at: March 9, 2026, 3:33 p.m.