Triple

T15032701
Position Surface form Disambiguated ID Type / Status
Subject Mike Edmonds E378392 entity
Predicate notableWork P4 FINISHED
Object Legend
Legend is a 1985 dark fantasy film directed by Ridley Scott, known for its fairy-tale world, striking visual style, and an early starring role for Tom Cruise.
E198720 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: Legend | Statement: [Mike Edmonds, notableWork, Legend]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Legend
Context triple: [Mike Edmonds, notableWork, Legend]
  • A. Legend
    Legend is the eighth studio album by American singer John Legend, showcasing his blend of R&B, soul, and pop influences.
  • B. Legend
    Legend is a performer known for their role in the work "Nervous."
  • C. Legend
    Legend is the highest honor bestowed in the Australian Football Hall of Fame, reserved for players and figures of exceptional and enduring significance to the sport.
  • D. Legend
    Legend was the original brand name of the Chinese technology company now known globally as Lenovo.
  • E. Legend
    Legend is a greatest hits compilation album by Bob Marley and the Wailers that has become one of the best-selling and most influential reggae records of all time.
  • 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: Legend
Triple: [Mike Edmonds, notableWork, Legend]
Generated description
Legend is a 1985 dark fantasy film directed by Ridley Scott, known for its fairy-tale world, striking visual style, and an early starring role for Tom Cruise.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Legend
Target entity description: Legend is a 1985 dark fantasy film directed by Ridley Scott, known for its fairy-tale world, striking visual style, and an early starring role for Tom Cruise.
  • A. Legend chosen
    Legend is a 1985 dark fantasy film directed by Ridley Scott, known for its lush visual style, fairy-tale atmosphere, and Tim Curry’s iconic portrayal of the Lord of Darkness.
  • B. Legend
    Legend is a dramatic film in which Colin Morgan appears, known for its portrayal of the notorious Kray twins in 1960s London.
  • C. Legend
    Legend is the eighth studio album by American singer John Legend, showcasing his blend of R&B, soul, and pop influences.
  • D. Legend
    Legend is a performer known for their role in the work "Nervous."
  • E. Legend
    Legend is the official mascot character created for the 2015 World Aquatics Championships held in Kazan, Russia.
  • F. None of above.

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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7e3a7c8819081f26c2435c1bcb2 completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9ddb46888190b1d2fe2992fc120b completed May 9, 2026, 2:37 a.m.
NEDg Description generation batch_69fe9efce5dc8190909b891c476d5291 completed May 9, 2026, 2:42 a.m.
NED2 Entity disambiguation (via description) batch_69fea2bd5d2c8190b26d2393cd8abb3e completed May 9, 2026, 2:58 a.m.
Created at: April 10, 2026, 2:59 a.m.