Triple
T33703588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billy Shaw |
E863524
|
entity |
| Predicate | choseToSignWith |
P177219
|
FINISHED |
| Object | Buffalo Bills |
—
|
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: Buffalo Bills | Statement: [Billy Shaw, choseToSignWith, Buffalo Bills]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: choseToSignWith Context triple: [Billy Shaw, choseToSignWith, Buffalo Bills]
-
A.
alsoSignedWith
Indicates that an entity signed or endorsed something together with another specified entity, as part of the same signing action or agreement.
-
B.
typicallySignedWith
Indicates that an entity is most commonly or customarily accompanied by a particular signature, mark, or signing method.
-
C.
coSignedWith
Indicates that an entity has jointly signed a document, agreement, or obligation together with another entity.
-
D.
hasSignFor
Indicates that one entity displays, bears, or provides a sign, symbol, or notice that represents, directs attention to, or gives information about another entity.
-
E.
signCanBe
Indicates that one sign is capable of serving as, or functioning in the role of, another specified sign.
- 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_69f3498844608190bb8f9b14908d2510 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fae2a7a8819099945d1706a94bfd |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f96dd4c8819093d6a7bd046a9ad5 |
completed | May 3, 2026, 7:29 a.m. |
| PDg | Predicate description generation | batch_69f6fa335b908190a20d92d5396203b5 |
completed | May 3, 2026, 7:33 a.m. |
Created at: May 1, 2026, 1:43 a.m.