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.