Triple
T34948686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runaway Bride |
E1007922
|
entity |
| Predicate | starsPreviouslyTeamedIn |
P153908
|
FINISHED |
| Object | Pretty Woman |
E218750
|
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: Pretty Woman | Statement: [Runaway Bride, starsPreviouslyTeamedIn, Pretty Woman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: starsPreviouslyTeamedIn Context triple: [Runaway Bride, starsPreviouslyTeamedIn, Pretty Woman]
-
A.
directorAlsoStarred
Indicates that the person who directed a work also acted or performed as a star in that same work.
-
B.
playedInEnsembleWith
Indicates that one entity has performed together with another as members of the same musical ensemble or group.
-
C.
hasSiblingCoStars
Indicates that two or more entities have appeared together as co-stars and are siblings in relation to each other.
-
D.
wasTeammateOf
Indicates that two entities were members of the same team during an overlapping period of time.
-
E.
notableCastWorkedWith
chosen
Indicates that there is a notable professional collaboration or working relationship between members of a cast.
- 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_69f76dc5d4308190b77553ee07b1ede6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f782ccb1ec8190a15e00c9e678e5da |
completed | May 3, 2026, 5:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37b2685a3081908f6ef6f9f79b5d63 |
completed | June 21, 2026, 9:44 a.m. |
| PD | Predicate disambiguation | batch_69f781020cc4819088c40cb8589504e4 |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 3, 2026, 4 p.m.