Triple
T18106590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mau Piailug |
E433359
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Mau Piailug |
—
|
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: Mau Piailug | Statement: [Mau Piailug, name, Mau Piailug]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mau Piailug Context triple: [Mau Piailug, name, Mau Piailug]
-
A.
Mau Piailug
chosen
Mau Piailug was a master Micronesian navigator renowned for reviving traditional non-instrument wayfinding and helping demonstrate the feasibility of ancient Polynesian voyaging.
-
B.
Moko Tepania
Moko Tepania is a New Zealand politician who serves as the mayor of the Far North District and is noted as one of the country’s youngest and first openly Māori leaders in that role.
-
C.
Wik-Mungkan
Wik-Mungkan is an Aboriginal Australian language traditionally spoken by the Wik peoples of western Cape York Peninsula in Queensland.
-
D.
Oluta Zoque
Oluta Zoque is a Zoquean language spoken by the indigenous Oluta Popoluca people in the state of Veracruz, Mexico.
-
E.
Sama-Banguingui
Sama-Banguingui is an Austronesian language spoken by the Sama-Banguingui people of the Sulu Archipelago in the southern 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_69d8b90916008190a1f110bd7ced5473 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddba6b288190af9a5d9c32d16e98 |
completed | April 19, 2026, 1:50 p.m. |
Created at: April 10, 2026, 10:28 a.m.