Triple
T27515015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Strother |
E694520
|
entity |
| Predicate | performedStuntsOn |
P45832
|
FINISHED |
| Object | skyscrapers |
—
|
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: skyscrapers | Statement: [Bill Strother, performedStuntsOn, skyscrapers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performedStuntsOn Context triple: [Bill Strother, performedStuntsOn, skyscrapers]
-
A.
stuntPerformerIn
Indicates that one entity serves as a stunt performer in a work, production, or performance associated with another entity.
-
B.
hasStunts
chosen
Indicates that one entity performs, includes, or is associated with stunt actions for another entity or context.
-
C.
performedTrick
Indicates that one entity executed or carried out a trick involving another entity or in a particular context.
-
D.
heroPerformsFor
Indicates that a hero carries out an action or performance for the benefit, entertainment, or service of another entity.
-
E.
performedStandUpOn
Indicates that one entity conducted or participated in a stand-up meeting on a specific date or occasion with respect to another entity.
- 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_69ef53842afc8190ba6bd4e4999bda67 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: April 27, 2026, 1:18 p.m.