Triple

T8628721
Position Surface form Disambiguated ID Type / Status
Subject Eli Loker E204344 entity
Predicate employer P7 FINISHED
Object Lightman Group E746382 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: Lightman Group | Statement: [Eli Loker, employer, Lightman Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lightman Group
Context triple: [Eli Loker, employer, Lightman Group]
  • A. Lightman Group chosen
    Lightman Group is a fictional deception-detection consulting firm from the TV series "Lie to Me," led by Dr. Cal Lightman and his team of experts.
  • B. Bell-Mason Group
    Bell-Mason Group is a consulting and advisory firm best known for developing the Bell-Mason Diagnostic, a framework for assessing and guiding the growth of technology startups and ventures.
  • C. Marshall Group
    Marshall Group is a British aerospace and defense company based in Cambridge, known for its aviation services, engineering, and property businesses.
  • D. Arroyo Group
    Arroyo Group is one of the architectural complexes within the ancient Zapotec archaeological site of Mitla in Oaxaca, Mexico.
  • E. Berkeley Group
    Berkeley Group is a major British property development company known for building large-scale residential and mixed-use projects, particularly in London and the South East of England.
  • 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_69ca834a4ea0819094970dceb9e389f3 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc473f6b888190ae40d65f24122c88 completed March 31, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69cecc9abd1081909d45af7498ec7c34 completed April 2, 2026, 8:07 p.m.
Created at: March 30, 2026, 6:27 p.m.