Triple

T23040087
Position Surface form Disambiguated ID Type / Status
Subject Somerset Collection E573709 entity
Predicate ownedBy P347 FINISHED
Object The Forbes Company 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: The Forbes Company | Statement: [Somerset Collection, ownedBy, The Forbes Company]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Forbes Company
Context triple: [Somerset Collection, ownedBy, The Forbes Company]
  • A. The Forbes Company chosen
    The Forbes Company is a U.S.-based real estate development firm known for creating and operating upscale, luxury shopping malls.
  • B. MacAndrews & Forbes
    MacAndrews & Forbes is a private holding company controlled by Ronald Perelman, known for its diversified investments across industries such as consumer products, entertainment, and defense.
  • C. Far Corporation
    Far Corporation was a German-based studio supergroup formed by producer Frank Farian, best known for its rock-oriented cover of Led Zeppelin’s “Stairway to Heaven” in the 1980s.
  • D. Forney Corporation
    Forney Corporation is an industrial equipment and systems company that operates as a business division of Graham Holdings Company.
  • E. Rand Company
    Rand Company was an American industrial firm known for manufacturing heavy machinery and equipment, which later became part of the Dresser-Rand corporate lineage.
  • 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_69e245b911188190bc3d96326c847969 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18512df708190a6892e743a289c74 completed April 29, 2026, 4:12 a.m.
Created at: April 17, 2026, 3:53 p.m.