Triple

T10396316
Position Surface form Disambiguated ID Type / Status
Subject Ashes to Ashes E245030 entity
Predicate actor P5563 FINISHED
Object Marshall Lancaster E868915 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: Marshall Lancaster | Statement: [Ashes to Ashes, actor, Marshall Lancaster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marshall Lancaster
Context triple: [Ashes to Ashes, actor, Marshall Lancaster]
  • A. Marshall Lancaster chosen
    Marshall Lancaster is a British actor best known for his role as DC Chris Skelton in the television series "Life on Mars" and its sequel "Ashes to Ashes."
  • B. Marshall Harvey
    Marshall Harvey is a film editor best known for his work on movies such as the dark comedy "The 'Burbs."
  • C. Scott Marshall
    Scott Marshall is an American film and television director known for his work on comedies and for being the son of filmmaker Garry Marshall.
  • D. Brian Marshall
    Brian Marshall was a British actor known for his supporting roles in film and television, including an appearance in the crime thriller "The Long Good Friday."
  • E. Marshall Pease
    Marshall Pease is a computer scientist best known for co-authoring the seminal paper that introduced the Byzantine Generals Problem in distributed computing and fault tolerance.
  • 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9cf79348190975d6c1791e3b621 completed April 7, 2026, 11:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69d95e4aef148190be58486605f85f77 completed April 10, 2026, 8:32 p.m.
Created at: April 6, 2026, 12:06 p.m.