Triple
T7856284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Midnight Yell |
E182382
|
entity |
| Predicate | startTimeRelativeToGame |
P79389
|
FINISHED |
| Object | midnight before game day |
—
|
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: midnight before game day | Statement: [Midnight Yell, startTimeRelativeToGame, midnight before game day]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeRelativeToGame Context triple: [Midnight Yell, startTimeRelativeToGame, midnight before game day]
-
A.
positionStartTime
Indicates the time at which a position, role, or placement begins.
-
B.
timeBehind
Indicates that one entity occurs or is positioned later in time than another, lagging behind it on a temporal scale.
-
C.
startTimeAsCardinal
Indicates the specific clock time at which an event or action begins, expressed as a cardinal (numeric) value rather than a textual or formatted time.
-
D.
timeStartApprox
Indicates that the associated event or state begins at an approximate, rather than exact, point in time.
-
E.
startTimeAsKing
Indicates the point in time at which an individual begins their reign or role as king.
- 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_69ca82887fd48190975896bf38c4596b |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb1a75de548190af5653409a3b3881 |
completed | March 31, 2026, 12:51 a.m. |
| PD | Predicate disambiguation | batch_69cae92180f88190ae3d44c3de7adc93 |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf786ec748190b6347b0c94335550 |
completed | March 30, 2026, 10:21 p.m. |
Created at: March 30, 2026, 4:52 p.m.