Triple
T9269666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angas–Sura subgroup |
E222792
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Angas language |
E788791
|
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: Angas language | Statement: [Angas–Sura subgroup, hasMember, Angas language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angas language Context triple: [Angas–Sura subgroup, hasMember, Angas language]
-
A.
Angas languages
chosen
Angas languages are a group of closely related Chadic languages spoken primarily in central Nigeria.
-
B.
Adang language
Adang language is a Papuan language spoken by the Adang people on Alor Island in Indonesia’s Alor archipelago.
-
C.
Angkola language
Angkola language is an Austronesian language of the Batak group spoken primarily by the Angkola people in North Sumatra, Indonesia.
-
D.
Ta-ang language
The Ta-ang language is a Mon–Khmer language spoken primarily by the Ta-ang (Palaung) ethnic group in parts of Myanmar, China, and neighboring regions.
-
E.
Angan languages
The Angan languages are a group of closely related Papuan languages spoken primarily in the highlands of southeastern Papua New Guinea.
- 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_69ca841ffe208190aa7bcffbef2f8379 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd074ef7408190b213c09491918132 |
completed | April 1, 2026, 11:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b1ecfadc81909adf95fbbc77c389 |
completed | April 4, 2026, 6:38 a.m. |
Created at: March 30, 2026, 7:33 p.m.