Triple

T16795880
Position Surface form Disambiguated ID Type / Status
Subject Little Toot E408229 entity
Predicate basedOnWorkAuthor P2806 FINISHED
Object Hardie Gramatky
Hardie Gramatky was an American artist, animator, and children's book author best known for creating the classic picture book "Little Toot."
E1233055 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: Hardie Gramatky | Statement: [Little Toot, basedOnWorkAuthor, Hardie Gramatky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hardie Gramatky
Context triple: [Little Toot, basedOnWorkAuthor, Hardie Gramatky]
  • A. Hardie
    Hardie is a Scottish surname notably borne by Keir Hardie, a pioneering leader of the British Labour movement.
  • B. Hardinge
    Hardinge is a British noble family name historically associated with prominent military and colonial administrators in the United Kingdom.
  • C. Mannington
    Mannington is a small settlement in Norfolk, England, situated near the historic Wolterton estate.
  • D. Hebel
    Hebel is a small rural town in southwestern Queensland, Australia, near the New South Wales border.
  • E. Rockwood
    Rockwood is a small rural village in southern Ontario, Canada, known for its scenic limestone cliffs, caves, and the nearby Rockwood Conservation Area.
  • 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: Hardie Gramatky
Triple: [Little Toot, basedOnWorkAuthor, Hardie Gramatky]
Generated description
Hardie Gramatky was an American artist, animator, and children's book author best known for creating the classic picture book "Little Toot."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hardie Gramatky
Target entity description: Hardie Gramatky was an American artist, animator, and children's book author best known for creating the classic picture book "Little Toot."
  • A. Hardie
    Hardie is a Scottish surname notably borne by Keir Hardie, a pioneering leader of the British Labour movement.
  • B. Hardinge
    Hardinge is a British noble family name historically associated with prominent military and colonial administrators in the United Kingdom.
  • C. Mannington
    Mannington is a small settlement in Norfolk, England, situated near the historic Wolterton estate.
  • D. Hebel
    Hebel is a small rural town in southwestern Queensland, Australia, near the New South Wales border.
  • E. Rockwood
    Rockwood is a small city in eastern Tennessee that forms part of the Knoxville metropolitan area.
  • 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2a96d888190a9876c3784bb7f95 completed April 18, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00ab109694819094c696904faf0418 completed May 10, 2026, 3:58 p.m.
NEDg Description generation batch_6a00ab8a416c819097ed3d6c915ac373 completed May 10, 2026, 4 p.m.
NED2 Entity disambiguation (via description) batch_6a00ac301f188190ae25d5ae7a39eb34 completed May 10, 2026, 4:02 p.m.
Created at: April 10, 2026, 5:22 a.m.