Triple
T36132549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Dragon Painter |
E1045060
|
entity |
| Predicate | hasFilmStarCouple |
P35186
|
FINISHED |
| Object | Sessue Hayakawa and Tsuru Aoki |
—
|
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: Sessue Hayakawa and Tsuru Aoki | Statement: [The Dragon Painter, hasFilmStarCouple, Sessue Hayakawa and Tsuru Aoki]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFilmStarCouple Context triple: [The Dragon Painter, hasFilmStarCouple, Sessue Hayakawa and Tsuru Aoki]
-
A.
marriagePartnerInFilm
Indicates that one person is the spouse or marriage partner of another person within the context of a specific film.
-
B.
hasSpouseActorsInLeads
Indicates that the primary leading roles in a work are performed by actors who are spouses of each other.
-
C.
isRomanticLeadOf
Indicates that one entity serves as the primary romantic partner or love-interest counterpart to another entity within a narrative or story.
-
D.
notableCouple
chosen
Indicates that two entities are widely recognized or documented as a couple in a notable or significant relationship.
-
E.
directorSpouseInCast
Indicates that a film’s director is married to someone who appears as a cast member in that same film.
- F. None of above.
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_69f76e36a4508190b5bfc8f594272a4c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fffbb5d0188190b6d168de8626ff68 |
completed | May 10, 2026, 3:29 a.m. |
| PD | Predicate disambiguation | batch_69fffa3bc1208190a277961385a4789f |
completed | May 10, 2026, 3:23 a.m. |
Created at: May 3, 2026, 4:08 p.m.