Triple

T2398096
Position Surface form Disambiguated ID Type / Status
Subject Zerubbabel E47696 entity
Predicate ledGroupSize P31691 FINISHED
Object Approximately 42,360 returnees (with others) according to Ezra 2 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: Approximately 42,360 returnees (with others) according to Ezra 2 | Statement: [Zerubbabel, ledGroupSize, Approximately 42,360 returnees (with others) according to Ezra 2]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: ledGroupSize
Context triple: [Zerubbabel, ledGroupSize, Approximately 42,360 returnees (with others) according to Ezra 2]
  • A. numberOfLights
    Indicates the quantity of lights associated with or present on a given entity.
  • B. numberOfGroups
    Indicates the total count of distinct groups associated with or formed within a given context or entity.
  • C. 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).
  • D. hasNumberOfMainLights
    Indicates the relationship that specifies how many primary or main lights are associated with an entity.
  • E. numberOfGroupMembers chosen
    Indicates the total count of individual members that belong to a specified group.
  • 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_69a88a1c450c81909f61abb8b6863885 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc8c5f0948190b4ea729693d8c306 completed March 7, 2026, 6:42 a.m.
PD Predicate disambiguation batch_69abc5a3825c81909ec6111dfc165453 completed March 7, 2026, 6:28 a.m.
Created at: March 4, 2026, 7:57 p.m.