Triple

T16064612
Position Surface form Disambiguated ID Type / Status
Subject Ubisoft E389699 entity
Predicate product P490 FINISHED
Object For Honor E1189709 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: For Honor | Statement: [Ubisoft, product, For Honor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: For Honor
Context triple: [Ubisoft, product, For Honor]
  • A. For Honor chosen
    For Honor is a medieval-themed action fighting game by Ubisoft that features intense melee combat between knights, samurai, and vikings in both single-player and multiplayer modes.
  • B. Battlelines
    Battlelines is a political memoir and policy manifesto by former Australian Prime Minister Tony Abbott, outlining his ideological views and vision for Australia's future.
  • C. Call of Heroes
    Call of Heroes is a 2016 Chinese-Hong Kong action film set in the early Republican era, known for its martial arts choreography and ensemble cast.
  • D. Sledgehammer
    "Sledgehammer" is a pop song by the girl group Fifth Harmony, known for its upbeat production and empowering breakup-themed lyrics.
  • E. Sledgehammer
    Sledgehammer is an automated theorem-proving tool integrated into the Isabelle proof assistant that invokes external provers to help discharge proof obligations.
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1837b048881908326739bbede756f completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe47ef6648190bf1fe216e78ef660 completed May 10, 2026, 1:50 a.m.
Created at: April 10, 2026, 4:57 a.m.