Triple

T14345939
Position Surface form Disambiguated ID Type / Status
Subject Sue Brierley E355719 entity
Predicate relatedPerson P37 FINISHED
Object Saroo Brierley E323597 NE 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: Saroo Brierley | Statement: [Sue Brierley, relatedPerson, Saroo Brierley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saroo Brierley
Context triple: [Sue Brierley, relatedPerson, Saroo Brierley]
  • A. Saroo Brierley chosen
    Saroo Brierley is an Indian-born Australian businessman and author best known for his memoir about finding his birth family using Google Earth, which inspired the film "Lion."
  • B. Saroo
    Saroo is an Indian-born Australian businessman and author best known for finding his birth family using Google Earth, a story depicted in the film "Lion."
  • C. Azaria
    Azaria is a given name used by various individuals, including the Israeli engineer and academic Azaria Paz.
  • D. Sydney Stevenson
    Sydney Stevenson is a British actress and writer, known for her work in television and theatre and for being part of a prominent acting family.
  • E. Lindy Chamberlain
    Lindy Chamberlain is an Australian woman whose conviction and later exoneration over the disappearance of her baby Azaria at Uluru became one of the country’s most infamous legal controversies.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d82790a7e08190877e2d349b2e8d8e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8e8b81bc8190ace2a575faf55cc0 completed April 14, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5508da0c8190a8ea44ca737cf352 completed May 8, 2026, 3:14 a.m.
Created at: April 10, 2026, 1:14 a.m.