Triple
T8342628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Papahānaumoku |
E195956
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Wākea |
E180852
|
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: Wākea | Statement: [Papahānaumoku, spouse, Wākea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wākea Context triple: [Papahānaumoku, spouse, Wākea]
-
A.
Wākea
chosen
Wākea is a prominent figure in Hawaiian mythology, often regarded as the sky father and a creator deity associated with the origins of the Hawaiian Islands and their people.
-
B.
Rongo
Rongo is a major Polynesian deity commonly associated with cultivated food, especially sweet potatoes, as well as peace and agriculture.
-
C.
Aquilon
Aquilon was a warship that engaged in naval combat with the British battleship HMS Goliath.
-
D.
Tui
Tui is a historic town in northwestern Spain’s Galicia region, known for its medieval architecture and strategic location on the border with Portugal.
-
E.
Maiar
The Maiar are powerful, angelic spirits in J.R.R. Tolkien’s legendarium who serve the Valar and often act as guides or guardians of the world, including figures like Gandalf and Sauron.
- 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_69ca82ecbdc481908a55cad8ca062d88 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7fe9efec81908e0c9ded3963bac5 |
completed | March 31, 2026, 8:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc72bc43c81909d95c7eb6aefc403 |
completed | April 2, 2026, 1:32 a.m. |
Created at: March 30, 2026, 5:58 p.m.