Triple

T10972236
Position Surface form Disambiguated ID Type / Status
Subject Famke Janssen E259268 entity
Predicate notableWork P4 FINISHED
Object Taken E178794 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: Taken | Statement: [Famke Janssen, notableWork, Taken]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taken
Context triple: [Famke Janssen, notableWork, Taken]
  • A. Taken chosen
    Taken is a 2008 action thriller film in which Liam Neeson plays a former CIA operative who relentlessly hunts down his daughter's kidnappers in Paris.
  • B. Stolen
    "Stolen" is a suspense thriller novel by Tess Gerritsen that follows a woman whose identity and life are suddenly erased, plunging her into a dangerous conspiracy.
  • C. Took
    Took is the hobbit family name of Peregrin “Pippin” Took, one of the central characters in J.R.R. Tolkien’s The Lord of the Rings.
  • D. Taken by Force
    Taken by Force is a 1977 hard rock/heavy metal studio album by German band Scorpions, known for its powerful guitar work and controversial original cover art.
  • E. The Taking
    The Taking is a horror novel by Dean Koontz that follows a couple facing an apocalyptic, seemingly alien invasion that blurs the line between supernatural and science fiction terror.
  • 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_69d6aa895f4c8190887a15460ef622f4 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7719b5edc81908c1019f81e78bd2e completed April 9, 2026, 9:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2d7a0b3dc819084fbda3227caf5b5 completed April 18, 2026, 1 a.m.
Created at: April 8, 2026, 9:24 p.m.