Triple

T17374135
Position Surface form Disambiguated ID Type / Status
Subject Survivors of the Flux E422389 entity
Predicate featuresCharacter P626 FINISHED
Object Swarm 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: Swarm | Statement: [Survivors of the Flux, featuresCharacter, Swarm]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swarm
Context triple: [Survivors of the Flux, featuresCharacter, Swarm]
  • A. Swarm
    Swarm is a creative work—likely a film, series, or literary piece—recognized as a significant contribution by Fam Udeorji.
  • B. Swarm
    Swarm is a work created by Michael Schaefer, recognized as one of his notable artistic or creative projects.
  • C. Swarm
    Swarm is Foursquare’s companion mobile app focused on lifelogging and social location sharing, allowing users to check in to places, track their movements, and connect with friends.
  • D. Swarm
    Swarm is the nickname of the Greensboro Swarm, an NBA G League basketball team based in Greensboro, North Carolina.
  • E. Swarm chosen
    Swarm is a powerful, ancient villain in the Doctor Who universe, known for his reality-warping abilities and central role as a primary antagonist in the Flux storyline.
  • 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_69d889d6535c81908be333c01deaec4e completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a6b71148190bb10e1fac400d6c3 completed April 19, 2026, 2:14 a.m.
Created at: April 10, 2026, 5:44 a.m.