Triple
T9727975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vickers Wellesley |
E235662
|
entity |
| Predicate | recordFlightDate |
P89674
|
FINISHED |
| Object | 1938-11-05 |
—
|
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: 1938-11-05 | Statement: [Vickers Wellesley, recordFlightDate, 1938-11-05]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordFlightDate Context triple: [Vickers Wellesley, recordFlightDate, 1938-11-05]
-
A.
winningFlightDate
Indicates the date on which the associated flight is determined to be the winning or selected one among a set of candidate flights.
-
B.
recordedOnDate
Indicates the specific calendar date on which an event, action, or piece of information was formally recorded.
-
C.
dateOfNotableFlight
chosen
Indicates the calendar date on which a particular notable or significant flight took place.
-
D.
flightNumberAtTimeOfEvent
Indicates the specific flight number associated with an entity at the time a particular event occurred.
-
E.
yearOfFlight
Indicates the specific calendar year in which a particular flight took place or is scheduled to occur.
- 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_69ca84d0fad481909cdd45aa77416c48 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e7af544819090a8a1adec41943c |
completed | April 1, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69cd03c6ffc88190a5e9569e19122ad5 |
completed | April 1, 2026, 11:38 a.m. |
Created at: March 30, 2026, 8:21 p.m.