Triple

T14765791
Position Surface form Disambiguated ID Type / Status
Subject Bad Words E346991 entity
Predicate writer P1360 FINISHED
Object Andrew Dodge
Andrew Dodge is a screenwriter best known for writing the comedy film "Bad Words," starring Jason Bateman.
E1119336 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: Andrew Dodge | Statement: [Bad Words, writer, Andrew Dodge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew Dodge
Context triple: [Bad Words, writer, Andrew Dodge]
  • A. Peter Dodge
    Peter Dodge is an architect best known for designing the Concord Pavilion, a prominent outdoor concert venue in Concord, California.
  • B. Matt Dodge
    Matt Dodge is a former NFL punter best known for his time with the New York Giants, particularly for a pivotal misplayed punt in a 2010 game against the Philadelphia Eagles.
  • C. Jack Deerson
    Jack Deerson is a cinematographer best known for his work on the 1971 road movie "Two-Lane Blacktop."
  • D. Dane Bowers
    Dane Bowers is a British singer, songwriter, and producer best known as a member of the late-1990s boy band Another Level and for his collaborations in UK garage music.
  • E. Bill Denbrough
    Bill Denbrough is a central member of the Losers' Club in Stephen King's horror universe, known for his leadership, stutter, and lifelong struggle against the shape-shifting entity known as It.
  • 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: Andrew Dodge
Triple: [Bad Words, writer, Andrew Dodge]
Generated description
Andrew Dodge is a screenwriter best known for writing the comedy film "Bad Words," starring Jason Bateman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Andrew Dodge
Target entity description: Andrew Dodge is a screenwriter best known for writing the comedy film "Bad Words," starring Jason Bateman.
  • A. Peter Dodge
    Peter Dodge is an architect best known for designing the Concord Pavilion, a prominent outdoor concert venue in Concord, California.
  • B. Matt Dodge
    Matt Dodge is a former NFL punter best known for his time with the New York Giants, particularly for a pivotal misplayed punt in a 2010 game against the Philadelphia Eagles.
  • C. Jack Deerson
    Jack Deerson is a cinematographer best known for his work on the 1971 road movie "Two-Lane Blacktop."
  • D. Dane Bowers
    Dane Bowers is a British singer, songwriter, and producer best known as a member of the late-1990s boy band Another Level and for his collaborations in UK garage music.
  • E. Bill Denbrough
    Bill Denbrough is a central member of the Losers' Club in Stephen King's horror universe, known for his leadership, stutter, and lifelong struggle against the shape-shifting entity known as It.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7f576c881909da70627f5897c94 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cf4cef081909fa62125f43b36bc completed May 8, 2026, 4:19 p.m.
NEDg Description generation batch_69fe1d66af94819091a84c2225cc7828 completed May 8, 2026, 5:29 p.m.
NED2 Entity disambiguation (via description) batch_69fe1e0089e08190a91f8683e683c371 completed May 8, 2026, 5:31 p.m.
Created at: April 10, 2026, 1:30 a.m.