Triple
T27362102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tifft Nature Preserve |
E685852
|
entity |
| Predicate | primaryFaunaType |
P950
|
FINISHED |
| Object | migratory birds |
—
|
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: migratory birds | Statement: [Tifft Nature Preserve, primaryFaunaType, migratory birds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryFaunaType Context triple: [Tifft Nature Preserve, primaryFaunaType, migratory birds]
-
A.
primaryAISpecies
Indicates that one species is the main or dominant species associated with a particular AI system or AI-related context.
-
B.
faunaCharacteristic
Indicates that an entity has a specific trait, feature, or quality related to animals or animal life.
-
C.
mainPreySpecies
Indicates the species that serves as the primary prey or main food source for a given predator.
-
D.
fauna
chosen
Indicates that an entity is an animal or part of the animal life associated with a particular place or context.
-
E.
dominantLargeTerrestrialVertebrates
Indicates that the referenced entities are the primary or most ecologically influential large land-dwelling vertebrate animals in a given context or environment.
- 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69ff3fb2318c81908a46c2f513608935 |
completed | May 9, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69ff3e96dcc48190819f6204680d84aa |
completed | May 9, 2026, 2:03 p.m. |
Created at: April 27, 2026, 11:54 a.m.