Triple
T264256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Midnight Yell Practice |
E5690
|
entity |
| Predicate | heldOn |
P9394
|
FINISHED |
| Object | night before Texas A&M home football games |
—
|
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: night before Texas A&M home football games | Statement: [Midnight Yell Practice, heldOn, night before Texas A&M home football games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldOn Context triple: [Midnight Yell Practice, heldOn, night before Texas A&M home football games]
-
A.
held
Indicates that one entity physically grasped, carried, or kept another entity in its possession or control.
-
B.
holding
Indicates that one entity is physically grasping, carrying, or keeping another entity in its possession or control.
-
C.
heldThat
Indicates that an entity (often a person or authority) maintained, asserted, or concluded that a particular proposition or judgment is true.
-
D.
recordHeld
Indicates that one entity possesses or maintains a particular record associated with another entity or context.
-
E.
isUsuallyHeldBy
Indicates that something is most commonly or typically possessed, carried, or controlled by 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_69a2587daeb081909591b9d30f80a271 |
completed | Feb. 28, 2026, 2:52 a.m. |
| NER | Named-entity recognition | batch_69a25d8e809881908a58c9a4e3ba07c3 |
completed | Feb. 28, 2026, 3:14 a.m. |
| PD | Predicate disambiguation | batch_69a25b6e07748190834022a65ba6d803 |
completed | Feb. 28, 2026, 3:05 a.m. |
| PDg | Predicate description generation | batch_69a25d0ec71081908478c800be4f7bb0 |
completed | Feb. 28, 2026, 3:12 a.m. |
Created at: Feb. 28, 2026, 2:56 a.m.