Triple
T2955856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlantic white-sided dolphin |
E79928
|
entity |
| Predicate | groupSize |
P8561
|
FINISHED |
| Object | often forms groups of 10 to several hundred individuals |
—
|
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: often forms groups of 10 to several hundred individuals | Statement: [Atlantic white-sided dolphin, groupSize, often forms groups of 10 to several hundred individuals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: groupSize Context triple: [Atlantic white-sided dolphin, groupSize, often forms groups of 10 to several hundred individuals]
-
A.
airGroupSize
Indicates the number of units or elements grouped together in an air-related context (such as aircraft in a formation or air assets in an operation).
-
B.
numberOfGroupMembers
Indicates the total count of individual members that belong to a specified group.
-
C.
typicalGroupSizeRange
chosen
Indicates the usual minimum and maximum number of individuals that typically occur together in a group for the given entity.
-
D.
numberOfGroups
Indicates the total count of distinct groups associated with or formed within a given context or entity.
-
E.
numberOfPersons
Indicates the total count of individual persons associated with or involved in a given entity, event, or context.
- 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_69ad8b1276588190a374a0b12e0f7bdf |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad99286ac8819084f02fbb0a1616d3 |
completed | March 8, 2026, 3:43 p.m. |
| PD | Predicate disambiguation | batch_69ad960c5c8881909d679912bd7d78f3 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:57 p.m.