Triple
T35494637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broughton Island |
E1025823
|
entity |
| Predicate | hasPrimaryFauna |
P153364
|
FINISHED |
| Object | seabirds |
—
|
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: seabirds | Statement: [Broughton Island, hasPrimaryFauna, seabirds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryFauna Context triple: [Broughton Island, hasPrimaryFauna, seabirds]
-
A.
hasWildlifeCharacteristic
Indicates that an entity possesses a particular trait, feature, or quality related to wildlife.
-
B.
hasMajorWildlife
chosen
Indicates that a location or area supports significant populations or habitats of important wildlife species.
-
C.
hasTerrestrialWildlife
Indicates that a location or environment contains or supports wildlife that lives primarily on land.
-
D.
hasNativeSpecies
Indicates that a particular species naturally occurs and evolved in a specified geographic area or habitat, rather than being introduced from elsewhere.
-
E.
faunaCharacteristic
Indicates that an entity has a specific trait, feature, or quality related to animals or animal life.
- 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_69f76dfc9c60819089c4217d93922615 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a04d8348190a4819666eab42c9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:04 p.m.