Triple
T1991726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Airlines Flight 77 |
E43264
|
entity |
| Predicate | impactTimeEasternDaylightTime |
P35236
|
FINISHED |
| Object | 09:37 |
—
|
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: 09:37 | Statement: [American Airlines Flight 77, impactTimeEasternDaylightTime, 09:37]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: impactTimeEasternDaylightTime Context triple: [American Airlines Flight 77, impactTimeEasternDaylightTime, 09:37]
-
A.
impactTimeLocal
Indicates the specific local time at which an impact event occurs or is expected to occur.
-
B.
isOneHourAheadOf
Indicates that one entity’s local time is exactly one hour later than the other entity’s local time.
-
C.
isTwoHoursAheadOf
Indicates that one entity’s time zone or local time is exactly two hours later than another entity’s.
-
D.
typicalKickoffTimeEastern
Indicates the usual starting time of an event, expressed in the Eastern Time zone.
-
E.
observedAsStandardTimeIn
Indicates that a particular time standard is used as the official or standard time within a specified place or region.
- 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_69a88714cf2c819081644be450b8356e |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8ee02dc81908fec9fd8df7a4f40 |
completed | March 7, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_69abb79ad6888190be99943a9c73cf3e |
completed | March 7, 2026, 5:28 a.m. |
| PDg | Predicate description generation | batch_69abb8ec608c81908917e945e0118ac4 |
completed | March 7, 2026, 5:34 a.m. |
Created at: March 4, 2026, 7:37 p.m.