Triple

T12944194
Position Surface form Disambiguated ID Type / Status
Subject Mrs. Sen's E309718 entity
Predicate mainCharacter P1183 FINISHED
Object Eliot E725074 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: Eliot | Statement: [Mrs. Sen's, mainCharacter, Eliot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eliot
Context triple: [Mrs. Sen's, mainCharacter, Eliot]
  • A. Eliot
    Eliot is the middle name of the American historian and naval officer Samuel Eliot Morison, known for his works on maritime and U.S. history.
  • B. Eliot chosen
    Eliot is a masculine given name of English origin, often associated with writers and public figures such as T.S. Eliot and Eliot Richardson.
  • C. Eliot
    Eliot is a light rail station on the MBTA Green Line D branch serving the Newton area of Greater Boston.
  • D. Thomas Lamb Eliot
    Thomas Lamb Eliot was a prominent American Unitarian minister and civic leader in Portland, Oregon, known for his influential role in the city’s religious, educational, and social institutions in the late 19th and early 20th centuries.
  • E. T. S. Eliot
    T. S. Eliot was a seminal 20th-century poet, critic, and playwright, best known for works such as "The Waste Land" and "Four Quartets," which profoundly influenced modernist literature.
  • 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_69d7bdfb57a88190836b743e2825feca completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97e1a28688190ab9fd1307bc76b4a completed April 10, 2026, 10:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6af73e6348190be114e8c5ad181bf completed May 3, 2026, 2:14 a.m.
Created at: April 9, 2026, 5:43 p.m.