Triple
T2332036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Airlines Flight 93 |
E44223
|
entity |
| Predicate | timeOfCrashLocal |
P33470
|
FINISHED |
| Object | 10:03 |
—
|
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: 10:03 | Statement: [United Airlines Flight 93, timeOfCrashLocal, 10:03]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfCrashLocal Context triple: [United Airlines Flight 93, timeOfCrashLocal, 10:03]
-
A.
impactTimeLocal
chosen
Indicates the specific local time at which an impact event occurs or is expected to occur.
-
B.
injuryOccurredAt
Indicates that an injury took place at a specific location or during a particular event or time.
-
C.
firstCrashDate
Indicates the date on which the first crash or failure event occurred for the entity in question.
-
D.
localTime
Indicates that a specific time value is expressed relative to a particular local time zone or locale, rather than in a universal or standardized time reference.
-
E.
endTimeLocal
Indicates the local date and time at which an event, activity, or state concludes.
- 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_69a889132b488190bbb43ad4780ddd92 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abcc30c5e881908c5d526d7e7491d0 |
completed | March 7, 2026, 6:56 a.m. |
| PD | Predicate disambiguation | batch_69abc5926d048190a535e3f23d41de2a |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:51 p.m.