Triple

T19809220
Position Surface form Disambiguated ID Type / Status
Subject Lambert Castle E475897 entity
Predicate originalOwner P347 FINISHED
Object Catholina Lambert NE NERFINISHED

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: Catholina Lambert | Statement: [Lambert Castle, originalOwner, Catholina Lambert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Catholina Lambert
Context triple: [Lambert Castle, originalOwner, Catholina Lambert]
  • A. Catholina Lambert chosen
    Catholina Lambert was a prominent 19th-century silk magnate and art collector based in Paterson, New Jersey.
  • B. Lusiana Burchard
    Lusiana Burchard is best known as the wife of renowned mathematician Sir Michael Atiyah.
  • C. Cecilia Noble
    Cecilia Noble is a British actress known for her work in theatre, television, and film, often praised for her strong character roles and comedic timing.
  • D. Cecile Landi
    Cecile Landi is a prominent French-American gymnastics coach best known for coaching Olympic champion Simone Biles and other elite U.S. gymnasts.
  • E. Ruby Lambert
    Ruby Lambert is the woman after whom the famous underground waterfall attraction Ruby Falls in Chattanooga, Tennessee, was named.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6542ac1b48190a0cb69dbceca74da completed April 20, 2026, 4:28 p.m.
Created at: April 10, 2026, 1:50 p.m.