Triple

T17909326
Position Surface form Disambiguated ID Type / Status
Subject Ghostfreak E447779 entity
Predicate enemyOf P437 FINISHED
Object Max Tennyson 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: Max Tennyson | Statement: [Ghostfreak, enemyOf, Max Tennyson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Max Tennyson
Context triple: [Ghostfreak, enemyOf, Max Tennyson]
  • A. Max Tennyson chosen
    Max Tennyson is the seasoned, resourceful grandfather and mentor figure who guides Ben and Gwen in their alien-fighting adventures in the "Ben 10" animated series.
  • B. Ben Tennyson
    Ben Tennyson is the young protagonist of the animated series "Ben 10," known for using the Omnitrix device to transform into various alien heroes and fight evil.
  • C. Owen Harper
    Owen Harper is a central character in the British sci-fi series "Torchwood," serving as the team's acerbic and brilliant medical officer.
  • D. Conrad Grayson
    Conrad Grayson is a powerful and morally corrupt businessman and political figure from the TV series "Revenge," serving as one of the show's primary antagonists.
  • E. Jarek Yeager
    Jarek Yeager is a seasoned former Rebel pilot and mechanic who runs a repair shop on the Colossus platform in the animated series Star Wars Resistance.
  • 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49e9f4f888190840c8b55672becf8 completed April 19, 2026, 9:21 a.m.
Created at: April 10, 2026, 10:19 a.m.