Triple
T19003925
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basilan |
E465025
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Yakan language |
—
|
NE NERFINISHED |
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: Yakan language | Statement: [Basilan, language, Yakan language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yakan language Context triple: [Basilan, language, Yakan language]
-
A.
Yakan language
chosen
The Yakan language is an Austronesian language spoken primarily by the Yakan people of the Sulu Archipelago and nearby areas in the southern Philippines.
-
B.
Butuanon language
The Butuanon language is an Austronesian language spoken primarily in and around Butuan City in Mindanao, Philippines.
-
C.
Kalagan language
The Kalagan language is an Austronesian language spoken by the Kalagan people of Mindanao in the southern Philippines, particularly in areas such as Sarangani.
-
D.
Maranao language
The Maranao language is an Austronesian language spoken primarily by the Maranao people around Lake Lanao in Mindanao, Philippines.
-
E.
Aborlan Tagbanwa language
The Aborlan Tagbanwa language is an Austronesian language spoken by the Tagbanwa people of Palawan in the Philippines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6a3db9c8190a1bf0228e360a6e0 |
completed | April 20, 2026, 7:32 a.m. |
Created at: April 10, 2026, 12:01 p.m.