Triple
T19551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chappaquiddick incident |
E388
|
entity |
| Predicate | timeOfAccident |
P302
|
FINISHED |
| Object | shortly before midnight |
—
|
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: shortly before midnight | Statement: [Chappaquiddick incident, timeOfAccident, shortly before midnight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfAccident Context triple: [Chappaquiddick incident, timeOfAccident, shortly before midnight]
-
A.
damageYear
Indicates the year in which the damage to an entity occurred or was recorded.
-
B.
timePeriod
chosen
Indicates the specific span or interval of time during which an event, state, or relationship occurs or is valid.
-
C.
dateOfRelatedEvent
Indicates that there is a specific date on which a related event associated with the subject occurs or occurred.
-
D.
damagedIn
Indicates that an entity has suffered harm, impairment, or destruction as a result of a specified event, process, or condition.
-
E.
tempo
Indicates the speed or pace at which an action, process, or sequence unfolds over time.
- 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_69a240778d288190815c0052ebbbcc91 |
completed | Feb. 28, 2026, 1:10 a.m. |
| NER | Named-entity recognition | batch_69a24703cb988190ad2bc181d27829e4 |
completed | Feb. 28, 2026, 1:38 a.m. |
| PD | Predicate disambiguation | batch_69a24650f1f0819081e638fafd18d687 |
completed | Feb. 28, 2026, 1:35 a.m. |
Created at: Feb. 28, 2026, 1:14 a.m.