Triple

T1065646
Position Surface form Disambiguated ID Type / Status
Subject Paul Bettany E23203 entity
Predicate notableWork P4 FINISHED
Object Legion
"Legion" is a 2010 supernatural action-horror film in which archangel Michael defies God to protect humanity from an impending apocalypse.
 E123981 NE FINISHED

How this triple was built (4 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: Legion | Statement: [Paul Bettany, notableWork, Legion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Legion
Context triple: [Paul Bettany, notableWork, Legion]
  • A. Green Lantern
    Green Lantern is a long-running DC Comics superhero franchise centered on intergalactic peacekeepers who wield power rings fueled by willpower.
  • B. Firestorm
    Firestorm is Apple’s high-performance ARM CPU core design used in the M1 chip to deliver fast, power-efficient processing.
  • C. The Sentry
    The Sentry is a 17th-century painting by Dutch Golden Age artist Carel Fabritius, noted for its subtle use of light and psychological depth in depicting a solitary guard.
  • D. New Earth
    New Earth is the renewed, perfected creation in Christian eschatology where the redeemed will dwell eternally in God’s presence.
  • E. McCloud
    McCloud is an American television crime drama series from the 1970s featuring a New Mexico lawman working with the New York City Police Department.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Legion
Triple: [Paul Bettany, notableWork, Legion]
Generated description
"Legion" is a 2010 supernatural action-horror film in which archangel Michael defies God to protect humanity from an impending apocalypse.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Legion
Target entity description: "Legion" is a 2010 supernatural action-horror film in which archangel Michael defies God to protect humanity from an impending apocalypse.
  • A. Green Lantern
    Green Lantern is a long-running DC Comics superhero franchise centered on intergalactic peacekeepers who wield power rings fueled by willpower.
  • B. Firestorm
    Firestorm is Apple’s high-performance ARM CPU core design used in the M1 chip to deliver fast, power-efficient processing.
  • C. The Sentry
    The Sentry is a 17th-century painting by Dutch Golden Age artist Carel Fabritius, noted for its subtle use of light and psychological depth in depicting a solitary guard.
  • D. New Earth
    New Earth is the renewed, perfected creation in Christian eschatology where the redeemed will dwell eternally in God’s presence.
  • E. McCloud
    McCloud is an American television crime drama series from the 1970s featuring a New Mexico lawman working with the New York City Police Department.
  • F. None of above. chosen

Provenance (5 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_69a493ee1f908190992b5f0d1b04459b completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b90f91248190ace1534a51b82bdd completed March 1, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac42a336388190a6d18fda8a7a151d completed March 7, 2026, 3:22 p.m.
NEDg Description generation batch_69ac43f306e48190b94f16749f5ba0d1 completed March 7, 2026, 3:27 p.m.
NED2 Entity disambiguation (via description) batch_69ac44467c9c8190a82ea8158add468a completed March 7, 2026, 3:29 p.m.
Created at: March 1, 2026, 7:42 p.m.