Triple
T2640485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Tyree |
E62852
|
entity |
| Predicate | ballSecuredAgainst |
P957
|
FINISHED |
| Object | helmet |
—
|
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: helmet | Statement: [David Tyree, ballSecuredAgainst, helmet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ballSecuredAgainst Context triple: [David Tyree, ballSecuredAgainst, helmet]
-
A.
ballSecurityError
Indicates that an error has occurred in enforcing or maintaining security constraints related to a ball-handling or ball-access operation.
-
B.
ballCondition
Indicates the specific state or status a ball is in, such as its physical condition, readiness for use, or compliance with required standards.
-
C.
areLockedIn
Indicates that the entities are confined within a space or situation from which they cannot freely exit or escape.
-
D.
protectedBy
chosen
Indicates that one entity provides protection, defense, or safeguarding for another entity.
-
E.
securityArrangementsBy
Indicates that one entity is responsible for providing, organizing, or overseeing security arrangements for another entity or situation.
- 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_69ab4c3f2dcc819082df80f5e032f690 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abd8fc8ee881908a9f6820d8934a62 |
completed | March 7, 2026, 7:51 a.m. |
| PD | Predicate disambiguation | batch_69abd812849881908f956845a80e0205 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:53 p.m.