Triple
T1528187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European starling |
E32382
|
entity |
| Predicate | flockingBehavior |
P18864
|
FINISHED |
| Object | forms murmurations |
—
|
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: forms murmurations | Statement: [European starling, flockingBehavior, forms murmurations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flockingBehavior Context triple: [European starling, flockingBehavior, forms murmurations]
-
A.
migratoryBehavior
Indicates the pattern, timing, and routes of movement that an entity follows when migrating from one location or region to another.
-
B.
swarmDensity
Indicates the concentration or number of individuals within a swarm relative to a given area or volume.
-
C.
territorialBehavior
Indicates a relationship where an entity actively defends or asserts control over a specific area or domain against others.
-
D.
formsSwarms
chosen
Indicates that multiple entities come together to create or participate in a coordinated swarm.
-
E.
behaviorNear
Indicates that one entity exhibits a behavior or action in close spatial proximity to 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_69a885e9b0ac819093a9806ad0efc82c |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a933ddc5a881909cdf503f2bc29bd4 |
completed | March 5, 2026, 7:42 a.m. |
| PD | Predicate disambiguation | batch_69a907ae8f688190ad9000ea1e018585 |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:26 p.m.