Triple

T2732386
Position Surface form Disambiguated ID Type / Status
Subject Elf E60344 entity
Predicate producer P490 FINISHED
Object Todd Komarnicki
Todd Komarnicki is an American screenwriter, producer, and director best known for writing the film "Sully" and producing the holiday classic "Elf."
 E294365 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: Todd Komarnicki | Statement: [Elf, producer, Todd Komarnicki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Todd Komarnicki
Context triple: [Elf, producer, Todd Komarnicki]
  • A. Mike Konopacki
    Mike Konopacki is an American political cartoonist known for his labor- and social-justice-focused comics and graphic works.
  • B. Joe Pisarcik
    Joe Pisarcik is a former NFL quarterback best known for his infamous late-game fumble in 1978 that led to the "Miracle at the Meadowlands."
  • C. Andrew Goczkowski
    Andrew Goczkowski is an American local government leader serving as the mayor of Des Plaines, Illinois.
  • D. Bill Neukom
    Bill Neukom is an American lawyer and philanthropist best known as Microsoft’s former chief legal officer and a former managing general partner of the San Francisco Giants.
  • E. Eric Szmanda
    Eric Szmanda is an American actor best known for playing forensic investigator Greg Sanders on the television series "CSI: Crime Scene Investigation."
  • 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: Todd Komarnicki
Triple: [Elf, producer, Todd Komarnicki]
Generated description
Todd Komarnicki is an American screenwriter, producer, and director best known for writing the film "Sully" and producing the holiday classic "Elf."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Todd Komarnicki
Target entity description: Todd Komarnicki is an American screenwriter, producer, and director best known for writing the film "Sully" and producing the holiday classic "Elf."
  • A. Mike Konopacki
    Mike Konopacki is an American political cartoonist known for his labor- and social-justice-focused comics and graphic works.
  • B. Joe Pisarcik
    Joe Pisarcik is a former NFL quarterback best known for his infamous late-game fumble in 1978 that led to the "Miracle at the Meadowlands."
  • C. Andrew Goczkowski
    Andrew Goczkowski is an American local government leader serving as the mayor of Des Plaines, Illinois.
  • D. Bill Neukom
    Bill Neukom is an American lawyer and philanthropist best known as Microsoft’s former chief legal officer and a former managing general partner of the San Francisco Giants.
  • E. Eric Szmanda
    Eric Szmanda is an American actor best known for playing forensic investigator Greg Sanders on the television series "CSI: Crime Scene Investigation."
  • 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_69ab4b75cd908190b691ef0d1801acda completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdaf011548190beb9c3feee7b743f completed March 7, 2026, 7:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69afbbc430ec8190a54f805cd0067b97 completed March 10, 2026, 6:35 a.m.
NEDg Description generation batch_69afbc545dc48190b61ed2ee73d53737 completed March 10, 2026, 6:38 a.m.
NED2 Entity disambiguation (via description) batch_69afbcd39c608190b01924370208f1ec completed March 10, 2026, 6:40 a.m.
Created at: March 6, 2026, 9:56 p.m.