Triple
T15901510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kapampangan people |
E385600
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | Pampangan |
E385601
|
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: Pampangan | Statement: [Kapampangan people, nativeName, Pampangan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pampangan Context triple: [Kapampangan people, nativeName, Pampangan]
-
A.
Pampangan
chosen
Pampangan is an alternative name for Kapampangan, an Austronesian language and ethnolinguistic group native to the Pampanga region in the Philippines.
-
B.
Pantanaw
Pantanaw is a town in Myanmar’s Ayeyarwady Region, historically noted as the birthplace of former UN Secretary-General U Thant.
-
C.
Paguay
Paguay is the former historic name of the city now known as Poway in San Diego County, California.
-
D.
Kaurareg
Kaurareg is a dialect of the Kalaw Lagaw Ya language traditionally spoken by the Kaurareg people of the Torres Strait in northern Australia.
-
E.
Tarempa
Tarempa is the main town and hub of government, commerce, and transportation in Indonesia’s Anambas Islands.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1563db01081908dd94a2536ef2107 |
completed | April 16, 2026, 9:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb04f3ea08190b5581768770677e8 |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.