Triple

T14250393
Position Surface form Disambiguated ID Type / Status
Subject Robert Downey Sr. E353244 entity
Predicate spouse P13 FINISHED
Object Elsie Ann Ford E156799 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: Elsie Ann Ford | Statement: [Robert Downey Sr., spouse, Elsie Ann Ford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elsie Ann Ford
Context triple: [Robert Downey Sr., spouse, Elsie Ann Ford]
  • A. Elsie Ann Ford chosen
    Elsie Ann Ford was an American actress and the mother of actor Robert Downey Jr.
  • B. Eleanor Clay Ford
    Eleanor Clay Ford was an American heiress and prominent Detroit philanthropist, best known as the wife of Edsel Ford and a key figure in the Ford family legacy.
  • C. Ethel Marion Foreman
    Ethel Marion Foreman was the first wife of acclaimed British actor Basil Rathbone, known primarily through her marriage to him.
  • D. Clara Jane Bryant Ford
    Clara Jane Bryant Ford was an American philanthropist and social activist best known as the longtime wife and partner of industrialist Henry Ford.
  • E. Edith Lyons
    Edith Lyons is a central character in the British dystopian drama series "Years and Years," known for her political activism and pivotal role in the show's depiction of a near-future UK.
  • 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_69d8278c43e08190824146f4632b89a5 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6296f9d0819086f62f525d07eb12 completed April 14, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69feb7cccd548190b9ec93f9d9d2f2af completed May 9, 2026, 4:27 a.m.
Created at: April 10, 2026, 1:08 a.m.