Triple
T513412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Auerbach |
E10653
|
entity |
| Predicate | signatureGesture |
P15416
|
FINISHED |
| Object | lighting a victory cigar on the bench |
—
|
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: lighting a victory cigar on the bench | Statement: [Red Auerbach, signatureGesture, lighting a victory cigar on the bench]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: signatureGesture Context triple: [Red Auerbach, signatureGesture, lighting a victory cigar on the bench]
-
A.
signature
Indicates that one entity has provided an official or personal signed endorsement, authorization, or acknowledgment on or for another entity.
-
B.
signatureEvent
Indicates an event in which an entity formally signs or authorizes something, such as a document, agreement, or record.
-
C.
signatureWork
Indicates that the work is a defining or most representative creation associated with an entity (such as a person, group, or organization).
-
D.
signatureImage
Indicates that an entity has an associated image that visually represents its signature.
-
E.
signatureStyle
Indicates the characteristic way in which an entity typically signs its name or marks documents, distinguishing its unique signing pattern or format.
- 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_69a2e84a0d08819087e01863fcd9abf1 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f232fa688190b08a2fe3f22c7a6e |
completed | Feb. 28, 2026, 1:48 p.m. |
| PD | Predicate disambiguation | batch_69a2f013c05481909e6dc87e7b20ebd8 |
completed | Feb. 28, 2026, 1:39 p.m. |
| PDg | Predicate description generation | batch_69a2f23214248190aa5fe1138f0f5a58 |
completed | Feb. 28, 2026, 1:48 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.