Triple
T13937748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Igede people |
E335162
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Igede language |
E335164
|
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: Igede language | Statement: [Igede people, language, Igede language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Igede language Context triple: [Igede people, language, Igede language]
-
A.
Igede language
chosen
Igede language is a Volta–Niger language spoken primarily by the Igede people of central Nigeria.
-
B.
Yidgha language
The Yidgha language is an Eastern Iranian language spoken in parts of northeastern Afghanistan, closely related to Munji and noted for preserving archaic features within the Pamir language group.
-
C.
Negidal language
The Negidal language is a critically endangered Tungusic language traditionally spoken by the Negidal people in the Russian Far East along the lower Amur River.
-
D.
Lasgerdi language
The Lasgerdi language is an Iranian language spoken in parts of north-central Iran and classified within the Semnani branch of Northwestern Iranian languages.
-
E.
Dida language
Dida language is a Niger-Congo language spoken primarily in Côte d'Ivoire, belonging to the Kru branch and known for its tonal and dialectal diversity.
- 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_69d81c6081b88190b53e317c3370c8fe |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2cf5cc8c8190bea74291702b2925 |
completed | April 14, 2026, 12:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7ce89d2348190b5a50376c2b8248c |
completed | May 3, 2026, 10:39 p.m. |
Created at: April 9, 2026, 10:17 p.m.