Triple

T16752008
Position Surface form Disambiguated ID Type / Status
Subject Three Ninjas Kick Back E407103 entity
Predicate starring P1507 FINISHED
Object Alan McRae
Alan McRae is an American actor best known for his role in the family martial arts comedy film "Three Ninjas Kick Back."
E1234800 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: Alan McRae | Statement: [Three Ninjas Kick Back, starring, Alan McRae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alan McRae
Context triple: [Three Ninjas Kick Back, starring, Alan McRae]
  • A. David McRae
    David McRae is an author known for his work on the song "Maria Maria."
  • B. Alister McRae
    Alister McRae is a Scottish rally driver who competed at international level, including in the World Rally Championship, and is the younger brother of the late world champion Colin McRae.
  • C. Guy McElwaine
    Guy McElwaine was an American film producer and talent agent known for his work in Hollywood during the late 20th century.
  • D. Andy MacMillan
    Andy MacMillan was a prominent Scottish architect known for his influential modernist church and public building designs in the mid-20th century.
  • E. Ken McMillan
    Ken McMillan is a prominent computer scientist known for his influential work in formal verification and model checking.
  • 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: Alan McRae
Triple: [Three Ninjas Kick Back, starring, Alan McRae]
Generated description
Alan McRae is an American actor best known for his role in the family martial arts comedy film "Three Ninjas Kick Back."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Alan McRae
Target entity description: Alan McRae is an American actor best known for his role in the family martial arts comedy film "Three Ninjas Kick Back."
  • A. David McRae
    David McRae is an author known for his work on the song "Maria Maria."
  • B. Alister McRae
    Alister McRae is a Scottish rally driver who competed at international level, including in the World Rally Championship, and is the younger brother of the late world champion Colin McRae.
  • C. Guy McElwaine
    Guy McElwaine was an American film producer and talent agent known for his work in Hollywood during the late 20th century.
  • D. Andy MacMillan
    Andy MacMillan was a prominent Scottish architect known for his influential modernist church and public building designs in the mid-20th century.
  • E. Ken McMillan
    Ken McMillan is a prominent computer scientist known for his influential work in formal verification and model checking.
  • 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_69d8838ffb088190a0b11149929006bf completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3aa282bb08190992c9b61caa7a345 completed April 18, 2026, 3:58 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b281cce881908c401bca3cf21dfc completed May 10, 2026, 4:29 p.m.
NEDg Description generation batch_6a00b399786c8190acbd188ab55b1fa0 completed May 10, 2026, 4:34 p.m.
NED2 Entity disambiguation (via description) batch_6a00b466ecd08190b7b5ee54476631ab completed May 10, 2026, 4:37 p.m.
Created at: April 10, 2026, 5:21 a.m.