Triple

T23251719
Position Surface form Disambiguated ID Type / Status
Subject Tabitha Hodge Broderick E581747 entity
Predicate middleName P143 FINISHED
Object Hodge 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: Hodge | Statement: [Tabitha Hodge Broderick, middleName, Hodge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hodge
Context triple: [Tabitha Hodge Broderick, middleName, Hodge]
  • A. Hodge chosen
    Hodge is a surname most notably associated with Charles Hodge, a prominent 19th-century American Presbyterian theologian.
  • B. Morgendorffer
    Morgendorffer is the surname of the central family in the animated television series "Daria," including its sardonic protagonist Daria Morgendorffer.
  • C. Hevery
    Hevery is the surname of Misko Hevery, a software engineer best known as the creator of the Angular web application framework.
  • D. Hodges
    Hodges is a small town located in Greenwood County in the state of South Carolina, United States.
  • E. Hodges
    Hodges is a surname most famously associated with Gil Hodges, the American Major League Baseball first baseman and manager.
  • 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_69e24606b17c81908aba1a4911c8a8ba completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f193f7249481909424867e9542d35e completed April 29, 2026, 5:15 a.m.
Created at: April 17, 2026, 4:11 p.m.