Triple
T30032443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Catch Me If You Can |
E763057
|
entity |
| Predicate | originalBroadwayFrankAbagnaleJrActor |
P4737
|
FINISHED |
| Object | Aaron Tveit |
—
|
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: Aaron Tveit | Statement: [Catch Me If You Can, originalBroadwayFrankAbagnaleJrActor, Aaron Tveit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalBroadwayFrankAbagnaleJrActor Context triple: [Catch Me If You Can, originalBroadwayFrankAbagnaleJrActor, Aaron Tveit]
-
A.
originalBroadwayDaveyActor
Indicates that the subject is the actor who played the role of Davey in the original Broadway production.
-
B.
originalBroadwayCaptainActor
Indicates that the subject is the actor who originally played the role of the ship’s captain in a Broadway production.
-
C.
originalBroadwayStar
chosen
Indicates that the subject was a member of the original Broadway cast in the specified role or production.
-
D.
broadwayLeadActor
Indicates that the subject is the principal or starring actor in a Broadway production associated with the object.
-
E.
portrayedInBroadwayProductionBy
Indicates that an entity was depicted or performed in a Broadway stage production by a specified person or group.
- 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_69f2246fb2b88190acff36bf7975c8f0 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a00037bf4148190a58593d30efdd3f8 |
completed | May 10, 2026, 4:03 a.m. |
| PD | Predicate disambiguation | batch_6a0000b7af608190b718fc4111bcdad8 |
completed | May 10, 2026, 3:51 a.m. |
Created at: April 29, 2026, 6:50 p.m.