Triple

T20819812
Position Surface form Disambiguated ID Type / Status
Subject Legion (2010 film) E512542 entity
Predicate character P662 FINISHED
Object Charlie
Charlie is a supporting character in the apocalyptic action-horror film "Legion" (2010), which centers on a group of people besieged by otherworldly forces at a remote desert diner.
E1453190 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: Charlie | Statement: [Legion (2010 film), character, Charlie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charlie
Context triple: [Legion (2010 film), character, Charlie]
  • A. Charlie
    Charlie is the ambitious New York City hustler and small-time crook who serves as the central protagonist in the crime drama film "The Pope of Greenwich Village."
  • B. Charlie
    Charlie is a fictional character portrayed by American actor Jared Rushton, best known for his roles in late-1980s films.
  • C. Charlie
    Charlie is a person whose full name is Charlie Watson.
  • D. Charlie
    Charlie is the central protagonist in the romantic film "Love, Wedding, Marriage," around whom the story’s relationship and marital themes revolve.
  • E. Charlie
    Charlie is a fictional character who serves as the central figure in the story "The Winner."
  • 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: Charlie
Triple: [Legion (2010 film), character, Charlie]
Generated description
Charlie is a supporting character in the apocalyptic action-horror film "Legion" (2010), which centers on a group of people besieged by otherworldly forces at a remote desert diner.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Charlie
Target entity description: Charlie is a supporting character in the apocalyptic action-horror film "Legion" (2010), which centers on a group of people besieged by otherworldly forces at a remote desert diner.
  • A. Charlie
    Charlie is the central protagonist of the apocalyptic horror film "Legion" (2010), a pregnant waitress whose unborn child is believed to be humanity’s last hope.
  • B. Charlie
    Charlie is a central character in the indie film "Happythankyoumoreplease," portrayed as a young New Yorker navigating relationships, personal growth, and the search for meaning.
  • C. Charlie
    Charlie is a central character in the romantic comedy film "French Kiss," serving as the unfaithful fiancé whose actions set the story’s events in motion.
  • D. Charlie
    Charlie is a fictional character from the television series "Deadwood," known as a loyal friend and ally of Wild Bill Hickok and Seth Bullock.
  • E. Charlie
    Charlie is the central protagonist of the film "The Business," around whom the story’s criminal and dramatic events revolve.
  • 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_69e0b4ce39108190a6e8e5df4f1c8dc5 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2f6a65481909a0df78616e185e4 completed April 21, 2026, 12:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a090077c1b4819097e2023cb63b3bb3 completed May 16, 2026, 11:40 p.m.
NEDg Description generation batch_6a0904888aa48190983a7102b22e9654 completed May 16, 2026, 11:58 p.m.
NED2 Entity disambiguation (via description) batch_6a0908594c3881909c7ef81dfb002c6f completed May 17, 2026, 12:14 a.m.
Created at: April 16, 2026, 12:41 p.m.