Triple
T22529380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawaiian mythology |
E556992
|
entity |
| Predicate | hasDeity |
P5606
|
FINISHED |
| Object | Hina |
—
|
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: Hina | Statement: [Hawaiian mythology, hasDeity, Hina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hina Context triple: [Hawaiian mythology, hasDeity, Hina]
-
A.
Hina
chosen
Hina is a prominent figure in Polynesian mythology, often depicted as a goddess associated with the moon, femininity, and skilled crafts.
-
B.
Hina-‘a
Hina-‘a is a variant name for Hina, a prominent goddess in Polynesian mythology often associated with the moon, creativity, and feminine power.
-
C.
Shuchi
Shuchi is a relatively obscure figure in Hindu mythology, known primarily as a child of Svaha and thus part of the divine lineage associated with the fire god Agni.
-
D.
Hana
Hana is a 2006 Japanese period drama film by director Hirokazu Kore-eda that blends a samurai revenge tale with gentle humanistic comedy and social commentary.
-
E.
Hana
Hana is a Japanese restaurant located within Tokyo Disney Resort’s Disney Ambassador Hotel, offering themed dining to hotel guests and park visitors.
- 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ed5b5d081909d927f8aee44b673 |
completed | April 29, 2026, 1:28 a.m. |
Created at: April 16, 2026, 8:51 p.m.