Triple
T29977754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Santos-Dumont 14-bis |
E761497
|
entity |
| Predicate | firstFlightPlace |
P14378
|
FINISHED |
| Object | Parc de Bagatelle, Paris, France |
—
|
NE NERFINISHED |
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: Parc de Bagatelle, Paris, France | Statement: [Santos-Dumont 14-bis, firstFlightPlace, Parc de Bagatelle, Paris, France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstFlightPlace Context triple: [Santos-Dumont 14-bis, firstFlightPlace, Parc de Bagatelle, Paris, France]
-
A.
allegedFirstFlightPlace
Indicates the location where an entity is claimed or reported to have made its first flight, without asserting that the claim is definitively true.
-
B.
firstFlightCity
Indicates the city from which an entity’s first flight departs.
-
C.
firstFlightFrom
Indicates that one entity is the earliest (chronologically first) flight departing from a given origin or on a given route among a set of flights.
-
D.
firstFlightLandingSite
Indicates the location where an aircraft or spacecraft completes its initial flight by landing.
-
E.
firstFlightLaunchSite
chosen
Indicates the location where an entity’s first flight was launched.
- 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_69f22467626081908d5afea489590e96 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a016777257081908841c5522dfa76e6 |
completed | May 11, 2026, 5:21 a.m. |
| PD | Predicate disambiguation | batch_6a0164e49bec8190af3c8626be9677a9 |
completed | May 11, 2026, 5:11 a.m. |
Created at: April 29, 2026, 6:34 p.m.