Triple

T5751437
Position Surface form Disambiguated ID Type / Status
Subject Doug Liman E126860 entity
Predicate directed P7373 FINISHED
Object Go
Go is a 1999 ensemble crime-comedy film known for its interlocking stories, fast-paced narrative, and energetic depiction of a wild night involving drugs, raves, and misadventures.
E548980 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: Go | Statement: [Doug Liman, directed, Go]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Go
Context triple: [Doug Liman, directed, Go]
  • A. Go
    Go is an ancient East Asian abstract strategy board game, renowned for its simple rules yet immense strategic depth, played on a grid with black and white stones.
  • B. Go
    Go is a statically typed, compiled programming language developed at Google, known for its simplicity, efficient concurrency support, and suitability for scalable networked and cloud services.
  • C. Go
    "Go" is a surf rock song, likely characterized by upbeat rhythms and guitar-driven melodies typical of the genre.
  • D. go90
    go90 was a now-defunct American mobile video streaming service owned by Verizon that offered live and on-demand sports, entertainment, and original programming.
  • E. Go (album)
    "Go" is a 2001 pop album by Italian singer Mario that showcases his melodic style and romantic themes.
  • 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: Go
Triple: [Doug Liman, directed, Go]
Generated description
Go is a 1999 ensemble crime-comedy film known for its interlocking stories, fast-paced narrative, and energetic depiction of a wild night involving drugs, raves, and misadventures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Go
Target entity description: Go is a 1999 ensemble crime-comedy film known for its interlocking stories, fast-paced narrative, and energetic depiction of a wild night involving drugs, raves, and misadventures.
  • A. Go
    Go is a statically typed, compiled programming language developed at Google, known for its simplicity, efficient concurrency support, and suitability for scalable networked and cloud services.
  • B. Go
    Go is an ancient East Asian abstract strategy board game, renowned for its simple rules yet immense strategic depth, played on a grid with black and white stones.
  • C. Go
    "Go" is a surf rock song, likely characterized by upbeat rhythms and guitar-driven melodies typical of the genre.
  • D. go90
    go90 was a now-defunct American mobile video streaming service owned by Verizon that offered live and on-demand sports, entertainment, and original programming.
  • E. Go (album)
    "Go" is a 2001 pop album by Italian singer Mario that showcases his melodic style and romantic themes.
  • 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_69c00832aedc81909899801b141fa3b4 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0288a0ea8819091ac6f965471ceee completed March 22, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c097fcba40819097543d151b890788 completed March 23, 2026, 1:31 a.m.
NEDg Description generation batch_69c098d889e08190adbd12504a7f3fa1 completed March 23, 2026, 1:35 a.m.
NED2 Entity disambiguation (via description) batch_69c09990da18819099fdc8f25f2ddef2 completed March 23, 2026, 1:38 a.m.
Created at: March 22, 2026, 3:48 p.m.