Triple
T25317853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cape gannet |
E634795
|
entity |
| Predicate | foragingAssociation |
P158381
|
FINISHED |
| Object | predatory fish |
—
|
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: predatory fish | Statement: [Cape gannet, foragingAssociation, predatory fish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foragingAssociation Context triple: [Cape gannet, foragingAssociation, predatory fish]
-
A.
foragingAssociation
chosen
Indicates a relationship where entities search for or obtain food in association with one another, typically sharing space, time, or coordination during foraging activities.
-
B.
foragingTendency
Indicates the degree to which an entity is inclined or likely to engage in searching for and gathering food or resources.
-
C.
hasForagingAbility
Indicates that an entity possesses the capability or skill to search for and obtain food or resources.
-
D.
foragingStratum
Indicates the vertical layer or height within a habitat where an organism typically searches for and obtains its food.
-
E.
foragingZone
Indicates the area or region where an entity typically searches for and collects food.
- 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_69e75a9847c08190bb02990d06d5ffb7 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f4968aece4819097e204da7b4e43cf |
completed | May 1, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 1:28 p.m.