Triple
T19056506
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | B'laan people |
E466408
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object | Blaan |
—
|
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: Blaan | Statement: [B'laan people, alternativeName, Blaan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blaan Context triple: [B'laan people, alternativeName, Blaan]
-
A.
Blaan
chosen
The Blaan are an indigenous ethnolinguistic group in southern Mindanao in the Philippines, known for their rich weaving traditions, brasswork, and distinct cultural practices.
-
B.
T’nalak
T’nalak is a sacred handwoven abaca cloth of the Tboli people of the Philippines, renowned for its intricate, dream-inspired patterns and deep cultural significance.
-
C.
Langata
Langata is a residential and suburban area in southwestern Nairobi, Kenya, known for attractions like Nairobi National Park and the Giraffe Centre.
-
D.
Tubatulabal
Tubatulabal are a Native American people indigenous to the Kern River Valley region of California, known for their distinct Uto-Aztecan language and cultural traditions.
-
E.
Lembá
Lembá is a coastal district on the island of São Tomé in São Tomé and Príncipe, known for its fishing communities and lush tropical landscapes.
- 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_69d8dd040fb881909af2a964f65ad208 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5dc067f788190b3b149dfee370435 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 10, 2026, 12:03 p.m.