Triple

T11528194
Position Surface form Disambiguated ID Type / Status
Subject Bruce Lee E273351 entity
Predicate studentOf P48 FINISHED
Object Ip Man E931915 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: Ip Man | Statement: [Bruce Lee, studentOf, Ip Man]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ip Man
Context triple: [Bruce Lee, studentOf, Ip Man]
  • A. Ip Man chosen
    Ip Man was a renowned Chinese martial artist and Wing Chun grandmaster best known as the teacher of Bruce Lee.
  • B. Drunken Master
    Drunken Master is a 1978 Hong Kong martial arts comedy film that helped establish Jackie Chan’s signature blend of acrobatic kung fu and slapstick humor.
  • C. Shaolin Kung Fu
    Shaolin Kung Fu is a historic Chinese martial arts tradition renowned for its rigorous physical training, intricate techniques, and deep roots in Chan (Zen) Buddhism.
  • D. Kung Fu
    Kung Fu is a 1970s American television series that blends martial arts action with Western drama, following a Shaolin monk’s spiritual and physical journey across the American Old West.
  • E. Wing Chun
    Wing Chun is a Chinese close-range martial art known for its efficient, direct techniques and emphasis on simultaneous attack and defense, famously studied by Bruce Lee.
  • 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_69d6aae3fbec8190a14632a5df2538b6 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d883972b10819093bd09cf8406671c completed April 10, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6e7e58d4081909647714975b55422 completed April 21, 2026, 2:58 a.m.
Created at: April 8, 2026, 9:37 p.m.