Triple

T9506386
Position Surface form Disambiguated ID Type / Status
Subject Tony Goldwyn E229279 entity
Predicate notableWork P4 FINISHED
Object Tarzan E67967 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: Tarzan | Statement: [Tony Goldwyn, notableWork, Tarzan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tarzan
Context triple: [Tony Goldwyn, notableWork, Tarzan]
  • A. Tarzan chosen
    Tarzan is a 1999 animated adventure film produced by Walt Disney Animation Studios, adapting Edgar Rice Burroughs’ story of a man raised by apes in the African jungle.
  • B. Tarzan
    Tarzan is a fictional jungle hero, raised by apes and known for his extraordinary strength, agility, and deep connection to the natural world.
  • C. Tarzan the Ape Man
    Tarzan the Ape Man is a 1932 adventure film that introduced Olympic swimmer Johnny Weissmuller in his iconic role as Edgar Rice Burroughs’ jungle hero Tarzan.
  • D. Tarzan and the Jungle Boy
    Tarzan and the Jungle Boy is a 1968 adventure film in the Tarzan franchise, featuring the jungle hero on a mission to find a missing boy in the African wilderness.
  • E. The Legend of Tarzan
    The Legend of Tarzan is a 2016 action-adventure film that reimagines Edgar Rice Burroughs’ classic jungle hero as he returns to the Congo to confront a deadly conspiracy.
  • 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_69ca847611c48190a28c028644198c75 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9852b7e48190a8f69cbde10d2858 completed April 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69d14c09b9f88190b279335b5289defb completed April 4, 2026, 5:36 p.m.
Created at: March 30, 2026, 7:57 p.m.