Triple
T30240267
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Santos-Dumont No. 5 |
E768892
|
entity |
| Predicate | flightObjective |
P79244
|
FINISHED |
| Object | controlled flight around the Eiffel Tower |
—
|
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: controlled flight around the Eiffel Tower | Statement: [Santos-Dumont No. 5, flightObjective, controlled flight around the Eiffel Tower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flightObjective Context triple: [Santos-Dumont No. 5, flightObjective, controlled flight around the Eiffel Tower]
-
A.
flightPurpose
chosen
Indicates the reason or intended purpose for which a particular flight is being taken or operated.
-
B.
flightOver
Indicates that one entity moves through the air above or across another entity or area.
-
C.
missionPilot
Indicates that an entity serves as the pilot responsible for operating or navigating a specific mission.
-
D.
flightRecord
Indicates a record of a specific flight event or journey, capturing details about its occurrence and characteristics.
-
E.
flightDisplay
Indicates that information about a flight is being shown or presented, typically on a screen or display system.
- 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_69f224820c048190b1435c4cc145acf1 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6804ea5148190a2b99a016b1644f5 |
completed | May 2, 2026, 10:53 p.m. |
| PD | Predicate disambiguation | batch_69f6760216108190bbb708d53a6c2c25 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:38 p.m.