Triple

T4367017
Position Surface form Disambiguated ID Type / Status
Subject Charles Luckman E98799 entity
Predicate employer P7 FINISHED
Object Lever Brothers E61784 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: Lever Brothers | Statement: [Charles Luckman, employer, Lever Brothers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lever Brothers
Context triple: [Charles Luckman, employer, Lever Brothers]
  • A. Chesebrough Manufacturing Company
    Chesebrough Manufacturing Company was an American petroleum-based products manufacturer best known for creating and popularizing Vaseline.
  • B. Procter & Gamble
    Procter & Gamble is a multinational consumer goods corporation known for a wide range of household, personal care, and hygiene brands sold globally.
  • C. United Brands Company
    United Brands Company was a major American agribusiness and food conglomerate best known as the successor to the United Fruit Company and a key player in the global banana trade.
  • D. Unilever chosen
    Unilever is a multinational consumer goods company known for its wide range of food, personal care, and household products sold globally.
  • E. Reckitt Benckiser
    Reckitt Benckiser is a British multinational consumer goods company best known for its health, hygiene, and home products such as Dettol, Lysol, and Durex.
  • 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_69b3454db3708190aeafd814413c4c3d completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b35201be7081908808e81634060f95 completed March 12, 2026, 11:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5dbcec90881908fe83c83119d99fe completed March 14, 2026, 10:06 p.m.
Created at: March 12, 2026, 11:17 p.m.