Triple

T20031656
Position Surface form Disambiguated ID Type / Status
Subject Traci Lords E497140 entity
Predicate notableWork P4 FINISHED
Object Blade
Blade is a 1998 superhero horror film based on the Marvel Comics character, following a half-vampire warrior who hunts vampires.
 E291496 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: Blade | Statement: [Traci Lords, notableWork, Blade]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Blade
Context triple: [Traci Lords, notableWork, Blade]
  • A. Blade
    Blade is the superhero-style mascot character of the Gold Coast Titans rugby league team in Australia's National Rugby League.
  • B. Blade
    Blade is a Marvel Comics vampire hunter and half-vampire antihero known for battling supernatural threats alongside teams like the Avengers.
  • C. Blade
    Blade is Laravel’s lightweight, PHP-based templating engine that lets developers write clean, reusable view templates with simple, expressive syntax.
  • D. Blade
    Blade is the nickname and given name of South African politician and academic Blade Nzimande, known for his leadership in the South African Communist Party and roles in government.
  • E. Blade
    Blade is a lethal, hook-handed puppet assassin from the horror film series "Puppet Master," known for his skeletal face, black trench coat, and prominent knife and hook weapons.
  • 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: Blade
Triple: [Traci Lords, notableWork, Blade]
Generated description
Blade is a 1998 superhero horror film based on the Marvel Comics character, following a half-vampire warrior who hunts vampires.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Blade
Target entity description: Blade is a 1998 superhero horror film based on the Marvel Comics character, following a half-vampire warrior who hunts vampires.
  • A. Blade chosen
    Blade is a Marvel Comics vampire hunter and half-vampire antihero known for battling supernatural threats alongside teams like the Avengers.
  • B. Blade
    Blade is the superhero-style mascot character of the Gold Coast Titans rugby league team in Australia's National Rugby League.
  • C. Blade
    Blade is Laravel’s lightweight, PHP-based templating engine that lets developers write clean, reusable view templates with simple, expressive syntax.
  • D. Blade
    Blade is the nickname and given name of South African politician and academic Blade Nzimande, known for his leadership in the South African Communist Party and roles in government.
  • E. Blade
    Blade is a lethal, hook-handed puppet assassin from the horror film series "Puppet Master," known for his skeletal face, black trench coat, and prominent knife and hook weapons.
  • 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_69da627278c88190babe4297a9df1236 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66292a80c81908adf95766b3b4ac4 completed April 20, 2026, 5:29 p.m.
NED1 Entity disambiguation (via context triple) batch_6a080e35085881909bdc753f10ab4425 completed May 16, 2026, 6:27 a.m.
NEDg Description generation batch_6a080f393dc0819093fec526d1b51dac completed May 16, 2026, 6:31 a.m.
NED2 Entity disambiguation (via description) batch_6a0810234a788190b329c55e553b365e completed May 16, 2026, 6:35 a.m.
Created at: April 11, 2026, 3:36 p.m.