Triple

T14702649
Position Surface form Disambiguated ID Type / Status
Subject Jock E345344 entity
Predicate friendOf P8712 FINISHED
Object Tramp E27476 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: Tramp | Statement: [Jock, friendOf, Tramp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tramp
Context triple: [Jock, friendOf, Tramp]
  • A. Tramp
    "Tramp" is a 1967 soul duet by Carla Thomas and Otis Redding that became one of their best-known collaborative hits.
  • B. The Tramp chosen
    The Tramp is Charlie Chaplin’s iconic silent-film character, a lovable vagrant known for his bowler hat, cane, and comedic yet poignant misadventures.
  • C. He's a Tramp
    "He's a Tramp" is a jazz-influenced song from Disney's 1955 animated film Lady and the Tramp, performed by the character Peg as she sings about the roguish dog Tramp.
  • D. The Lady Is a Tramp
    "The Lady Is a Tramp" is a popular show tune from the 1937 Rodgers and Hart musical "Babes in Arms," later becoming a jazz and pop standard widely recorded by major artists.
  • E. Tramps
    Tramps is a 2016 romantic comedy film about two young New Yorkers who are thrown together by a botched briefcase exchange, directed by Adam Leon and starring Callum Turner.
  • 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_69d822e4a8c08190a155df736bb7bc13 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb6071e5c8190bb5509c859135c2d completed April 14, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cdfb09481908021a3fc92962a00 completed May 8, 2026, 4:18 p.m.
Created at: April 10, 2026, 1:28 a.m.