Triple

T21497248
Position Surface form Disambiguated ID Type / Status
Subject Albrecht v. Herald Co. E530386 entity
Predicate respondent P2238 FINISHED
Object Herald Co. 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: Herald Co. | Statement: [Albrecht v. Herald Co., respondent, Herald Co.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Herald Co.
Context triple: [Albrecht v. Herald Co., respondent, Herald Co.]
  • A. Herald-Traveler Corporation chosen
    Herald-Traveler Corporation was a Boston-based media company best known for owning and operating newspapers and broadcast outlets in the mid-20th century.
  • B. T. B. Harms Company
    T. B. Harms Company was a prominent early 20th-century American music publishing firm known for issuing popular songs and standards from the Tin Pan Alley era.
  • C. Hahn Company
    Hahn Company was a real estate development firm that became part of the lineage leading to the major North American property company TrizecHahn.
  • D. The Hurwitz Company
    The Hurwitz Company is a television production company best known for producing the Netflix comedy series "Lady Dynamite."
  • E. Hart-Parr Company
    Hart-Parr Company was an early 20th-century American agricultural machinery manufacturer best known for pioneering the mass production of gasoline-powered farm tractors.
  • 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_69e0c45bd15481909fba5910765cdda2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea58faa08190ab9f60b0db3c425b completed April 23, 2026, 9:46 a.m.
Created at: April 16, 2026, 6:23 p.m.