Triple
T29977778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Santos-Dumont 14-bis |
E761497
|
entity |
| Predicate | laterFlightDate |
P197797
|
FINISHED |
| Object | 1906-11-12 |
—
|
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: 1906-11-12 | Statement: [Santos-Dumont 14-bis, laterFlightDate, 1906-11-12]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterFlightDate Context triple: [Santos-Dumont 14-bis, laterFlightDate, 1906-11-12]
-
A.
secondFlightDate
Indicates the date on which an entity undertakes its second flight or airborne operation.
-
B.
subsequentArrivalDate
Indicates that one entity’s arrival date occurs after the arrival date of another related entity.
-
C.
testFlightDate
Indicates the date on which a test flight for an entity (such as an aircraft or spacecraft) is scheduled or took place.
-
D.
flightStartDate
Indicates the date on which a particular flight is scheduled to begin or depart.
-
E.
winningFlightDate
Indicates the date on which the associated flight is determined to be the winning or selected one among a set of candidate flights.
- 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_69f22467626081908d5afea489590e96 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69feabcda59481908f2bc13b46fcced1 |
completed | May 9, 2026, 3:36 a.m. |
| PD | Predicate disambiguation | batch_69feaabd63f88190b30dcf6dd2ea39d1 |
completed | May 9, 2026, 3:32 a.m. |
| PDg | Predicate description generation | batch_69feabcca6148190a8eb7b6fa33729c7 |
completed | May 9, 2026, 3:36 a.m. |
Created at: April 29, 2026, 6:34 p.m.