Triple
T34195483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WUSA |
E877226
|
entity |
| Predicate | featuresSpouseCoStars |
P121091
|
FINISHED |
| Object | Paul Newman and Joanne Woodward |
E580271
|
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: Paul Newman and Joanne Woodward | Statement: [WUSA, featuresSpouseCoStars, Paul Newman and Joanne Woodward]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresSpouseCoStars Context triple: [WUSA, featuresSpouseCoStars, Paul Newman and Joanne Woodward]
-
A.
directorSpouseInCast
Indicates that a film’s director is married to someone who appears as a cast member in that same film.
-
B.
spouseAppearsIn
chosen
Indicates that the spouse of a given person appears or is featured in a specified work, context, or setting.
-
C.
hasSpouseActorsInLeads
Indicates that the primary leading roles in a work are performed by actors who are spouses of each other.
-
D.
filmCoStar
Indicates that two people appeared together as co-actors in the same film.
-
E.
marriagePartnerInFilm
Indicates that one person is the spouse or marriage partner of another person within the context of a specific film.
- F. None of above.
Provenance (4 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_69f349af20a4819089ac24d28f2d8112 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a030c7d03308190a102689db1e8b657 |
completed | May 12, 2026, 11:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36cc85da648190b504e88121faad64 |
completed | June 20, 2026, 5:23 p.m. |
| PD | Predicate disambiguation | batch_6a030a57b16c81909191270f64a77fcf |
completed | May 12, 2026, 11:09 a.m. |
Created at: May 1, 2026, 1:55 a.m.