Triple
T7580000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karay-a language |
E179460
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object | Antiqueño Karay-a |
E675070
|
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: Antiqueño Karay-a | Statement: [Karay-a language, hasDialect, Antiqueño Karay-a]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Antiqueño Karay-a Context triple: [Karay-a language, hasDialect, Antiqueño Karay-a]
-
A.
Karakays
Karakays are an ethnic community historically associated with the region of Gözleve (modern-day Yevpatoria) in Crimea.
-
B.
Karay-a
Karay-a is an Austronesian language spoken primarily by the Karay-a people in the Western Visayas region of the Philippines.
-
C.
Daang Matuwid
Daang Matuwid is the reform-focused governance platform and anti-corruption banner associated with the presidency of Benigno S. Aquino III in the Philippines.
-
D.
Iloilo Karay-a
chosen
Iloilo Karay-a is a regional variety of the Karay-a language spoken primarily in the province of Iloilo in the Philippines.
-
E.
Ikalahan
Ikalahan is an indigenous people of the northern Philippines whose name is also used for their native Kalanguya language.
- 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_69c69f327db881909a21ae3b156f8ded |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f975bbc08190aec30f902eaea494 |
completed | March 27, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8683deac48190bf953088c6c232d5 |
completed | March 28, 2026, 11:46 p.m. |
Created at: March 27, 2026, 3:52 p.m.