Triple
T24710329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Zealand falcon |
E612007
|
entity |
| Predicate | flightCharacteristic |
P134910
|
FINISHED |
| Object | swift |
—
|
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: swift | Statement: [New Zealand falcon, flightCharacteristic, swift]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flightCharacteristic Context triple: [New Zealand falcon, flightCharacteristic, swift]
-
A.
hasFlightCharacteristic
chosen
Indicates that an entity possesses a specific property, quality, or behavior related to flight.
-
B.
takeoffCharacteristic
Indicates the specific properties or conditions associated with how an entity takes off, such as its manner, performance, or requirements during takeoff.
-
C.
flightStyle
Indicates the characteristic manner or pattern in which an entity performs or exhibits flight.
-
D.
flightAbility
Indicates the capability or potential of an entity to fly or engage in powered or unpowered aerial movement.
-
E.
flightDeckFeature
Indicates that one entity is a feature, component, or element that is part of or present on the flight deck of another entity.
- 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_69e2c4d9c24c8190a3712d74327f0c6e |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f410fe3b848190ae296a29f742ee30 |
completed | May 1, 2026, 2:33 a.m. |
| PD | Predicate disambiguation | batch_69f40ee8ada8819089a7016b50308ff0 |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 3:24 a.m.