Triple

T11499030
Position Surface form Disambiguated ID Type / Status
Subject Shrek 2 E272615 entity
Predicate basedOnWorkBy P2806 FINISHED
Object William Steig E341039 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: William Steig | Statement: [Shrek 2, basedOnWorkBy, William Steig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Steig
Context triple: [Shrek 2, basedOnWorkBy, William Steig]
  • A. William Steig chosen
    William Steig was an American cartoonist and children’s book author best known for creating the character Shrek, which inspired the popular animated film series.
  • B. Maurice Sendak
    Maurice Sendak was an influential American illustrator and writer of children's books, best known for his classic picture book "Where the Wild Things Are."
  • C. Ludwig Bemelmans
    Ludwig Bemelmans was an Austrian-born American writer and illustrator best known as the creator of the beloved "Madeline" children's book series.
  • D. Eric Carle
    Eric Carle was an American author and illustrator best known for his distinctive collage-style artwork and beloved children's books such as "The Very Hungry Caterpillar."
  • E. Norton Juster
    Norton Juster was an American architect and author best known for his classic children's fantasy novel "The Phantom Tollbooth."
  • 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_69d6aae1b09881909ce2ded3fa0c14fa completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d85de27db081909ccdb4ab0ef75bdb completed April 10, 2026, 2:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69e604aa9e3c8190ad86e4d05a67c8ac completed April 20, 2026, 10:49 a.m.
Created at: April 8, 2026, 9:36 p.m.