Triple
T10964347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Houdini |
E259056
|
entity |
| Predicate | performedTrick |
P96883
|
FINISHED |
| Object | straitjacket escape |
—
|
LITERAL 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: straitjacket escape | Statement: [Harry Houdini, performedTrick, straitjacket escape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performedTrick Context triple: [Harry Houdini, performedTrick, straitjacket escape]
-
A.
performedWith
Indicates that an action or activity is carried out using, accompanied by, or in conjunction with a specified entity or instrument.
-
B.
performedPuppetryFor
Indicates that one entity carried out a puppetry performance for the benefit, entertainment, or purpose of another entity.
-
C.
hasAnimalTrainerInvolved
Indicates that an animal trainer is involved in or associated with the action, event, or relationship described.
-
D.
hasStunts
Indicates that one entity performs, includes, or is associated with stunt actions for another entity or context.
-
E.
performedTo
Indicates that an action or performance is directed toward or carried out on a particular entity.
- F. None of above. chosen
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_69d6aa88500c819097d7032ca578e74f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d77147f7108190a3b68ba1dd1c130e |
completed | April 9, 2026, 9:28 a.m. |
| PD | Predicate disambiguation | batch_69d72e8c27cc81908050590b7a04cafd |
completed | April 9, 2026, 4:43 a.m. |
| PDg | Predicate description generation | batch_69d7322370648190ba14cdd6fb4cdcb0 |
completed | April 9, 2026, 4:59 a.m. |
Created at: April 8, 2026, 9:23 p.m.