Triple

T14708962
Position Surface form Disambiguated ID Type / Status
Subject San Diego Comic-Con E345496 entity
Predicate founder P104 FINISHED
Object Shel Dorf
Shel Dorf was an American comics enthusiast and organizer best known for helping create and develop San Diego Comic-Con into a major pop culture convention.
E1115968 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: Shel Dorf | Statement: [San Diego Comic-Con, founder, Shel Dorf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shel Dorf
Context triple: [San Diego Comic-Con, founder, Shel Dorf]
  • A. Jo Eisinger
    Jo Eisinger was an American screenwriter best known for his dark, psychologically complex film noir scripts, including classics like "Gilda" and "Night and the City."
  • B. Jody Gerson
    Jody Gerson is a prominent American music executive and producer, best known as the CEO and Chairman of Universal Music Publishing Group.
  • C. Lee Stimmel
    Lee Stimmel is a television writer and producer best known for co-creating the animated comedy series "Mike Tyson Mysteries."
  • D. Cliff Dorfman
    Cliff Dorfman is an American screenwriter and filmmaker best known for co-writing the acclaimed sports drama film "Warrior" (2011).
  • E. Jon Shestack
    Jon Shestack is an American film producer known for working on a range of studio and independent movies, including the romantic comedy-drama "Dan in Real Life."
  • 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: Shel Dorf
Triple: [San Diego Comic-Con, founder, Shel Dorf]
Generated description
Shel Dorf was an American comics enthusiast and organizer best known for helping create and develop San Diego Comic-Con into a major pop culture convention.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Shel Dorf
Target entity description: Shel Dorf was an American comics enthusiast and organizer best known for helping create and develop San Diego Comic-Con into a major pop culture convention.
  • A. Jo Eisinger
    Jo Eisinger was an American screenwriter best known for his dark, psychologically complex film noir scripts, including classics like "Gilda" and "Night and the City."
  • B. Jody Gerson
    Jody Gerson is a prominent American music executive and producer, best known as the CEO and Chairman of Universal Music Publishing Group.
  • C. Lee Stimmel
    Lee Stimmel is a television writer and producer best known for co-creating the animated comedy series "Mike Tyson Mysteries."
  • D. Cliff Dorfman
    Cliff Dorfman is an American screenwriter and filmmaker best known for co-writing the acclaimed sports drama film "Warrior" (2011).
  • E. Jon Shestack
    Jon Shestack is an American film producer known for working on a range of studio and independent movies, including the romantic comedy-drama "Dan in Real Life."
  • 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_69d822e4a8c08190a155df736bb7bc13 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb609965081908f654bcb9eaaa145 completed April 14, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdf08a81948190ab903e5b8bfb0c81 completed May 8, 2026, 2:17 p.m.
NEDg Description generation batch_69fdf396b65c819088e2f350364fbfae completed May 8, 2026, 2:30 p.m.
NED2 Entity disambiguation (via description) batch_69fdf421390481909cb43aec3ef18d53 completed May 8, 2026, 2:33 p.m.
Created at: April 10, 2026, 1:28 a.m.