Triple

T15576963
Position Surface form Disambiguated ID Type / Status
Subject Marc Spector E374392 entity
Predicate enemy P4567 FINISHED
Object Bushman E969254 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: Bushman | Statement: [Marc Spector, enemy, Bushman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bushman
Context triple: [Marc Spector, enemy, Bushman]
  • A. Bushman chosen
    Bushman is a brutal mercenary and recurring supervillain in Marvel Comics, best known as one of Moon Knight’s primary adversaries.
  • B. Murle
    The Murle are a Nilotic ethnic group primarily inhabiting parts of South Sudan, known for their pastoralist lifestyle and distinct cultural traditions.
  • C. Basarwa
    Basarwa are indigenous hunter-gatherer peoples of Southern Africa, commonly known as the San or Bushmen, noted for their ancient rock art, click-language speech, and deep ecological knowledge of the Kalahari region.
  • D. Virginia Bushman
    Virginia Bushman was an American silent film actress and the daughter of prominent silent screen star Francis X. Bushman.
  • E. Mirambo
    Mirambo was a powerful 19th-century Nyamwezi warlord and trader in present-day Tanzania, known for building a strong kingdom and controlling key caravan trade routes.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e22c89081909b1ec0cd36a1ef45 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4978ec8190a57de5d9a2ec6653 completed May 9, 2026, 3:01 p.m.
Created at: April 10, 2026, 4:11 a.m.