Triple

T9451946
Position Surface form Disambiguated ID Type / Status
Subject Community E227914 entity
Predicate creator P184 FINISHED
Object Dan Harmon E257607 NE FINISHED

How this triple was built (2 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: Dan Harmon | Statement: [Community, creator, Dan Harmon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dan Harmon
Context triple: [Community, creator, Dan Harmon]
  • A. Dan Harmon chosen
    Dan Harmon is an American writer, producer, and showrunner best known for creating the sitcom "Community" and co-creating the animated series "Rick and Morty."
  • B. Michael Daves
    Michael Daves is an American bluegrass and roots musician known for his high-energy vocal style and collaborations with prominent artists such as mandolinist Chris Thile.
  • C. Jon Abrahams
    Jon Abrahams is an American actor best known for his comedic and horror film roles in the early 2000s, including prominent parts in popular parody and teen movies.
  • D. Spencer Kaling
    Spencer Kaling is the daughter of American actress, writer, and producer Mindy Kaling.
  • E. Michael Schur
    Michael Schur is an American television writer and producer best known for co-creating acclaimed comedy series such as Parks and Recreation, The Good Place, and Brooklyn Nine-Nine.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca8439f8bc8190997f2ef40c9f0bc2 completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd7f6796d8819088cbecc0588ae5fc completed April 1, 2026, 8:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69d12272a2dc8190892a22db0799b6a4 completed April 4, 2026, 2:38 p.m.
Created at: March 30, 2026, 7:52 p.m.