Triple

T19150950
Position Surface form Disambiguated ID Type / Status
Subject Harman Blennerhassett E468805 entity
Predicate givenName P17 FINISHED
Object Harman 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: Harman | Statement: [Harman Blennerhassett, givenName, Harman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harman
Context triple: [Harman Blennerhassett, givenName, Harman]
  • A. Harman chosen
    Harman is a given name and surname used in various cultures, often considered a variant of the name Hermann.
  • B. Harman Sullivan
    Harman Sullivan is a supporting character in the 1973 crime film "Charley Varrick," serving as the protagonist’s partner in a risky bank heist.
  • C. Leumann
    Leumann is a surname of likely Germanic or Swiss origin borne by individuals such as academic and public figure Christian Leumann.
  • D. Harman-Ising Studio
    Harman-Ising Studio was an early American animation studio founded by Hugh Harman and Rudolf Ising, best known for creating and producing some of the first Looney Tunes and Merrie Melodies cartoons.
  • E. Lord & Hewlett
    Lord & Hewlett was an American architectural firm active in the early 20th century, known for designing significant public and institutional buildings.
  • 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e97cfaa08190b7085d28fe970108 completed April 20, 2026, 8:53 a.m.
Created at: April 10, 2026, 12:06 p.m.