Triple

T9548241
Position Surface form Disambiguated ID Type / Status
Subject Frank Mills E230349 entity
Predicate notableWork P4 FINISHED
Object Peter Piper E440963 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: Peter Piper | Statement: [Frank Mills, notableWork, Peter Piper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Piper
Context triple: [Frank Mills, notableWork, Peter Piper]
  • A. Peter Piper chosen
    Peter Piper is a classic English-language tongue-twister character best known from the rhyme about picking a peck of pickled peppers.
  • B. Pete
    Pete is a common masculine given name, typically used as a familiar or informal form of the name Peter.
  • C. Pete
    Pete is a classic Disney cartoon villain, best known as Mickey Mouse’s burly, antagonistic foe in the Mickey Mouse franchise.
  • D. Pete
    Pete is a fictional character known as the son of Uncle Tom in Harriet Beecher Stowe’s anti-slavery novel "Uncle Tom’s Cabin."
  • E. Pete
    Pete is the nickname of Grover Cleveland Alexander, a Hall of Fame Major League Baseball pitcher and one of the greatest hurlers of the early 20th century.
  • 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_69ca847c70b8819088a0a0bad64a50d6 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9904732c8190ab60ecc47c995cbe completed April 1, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69d14c7be5008190a16036525fd9059e completed April 4, 2026, 5:38 p.m.
Created at: March 30, 2026, 8:02 p.m.