Triple

T26962668
Position Surface form Disambiguated ID Type / Status
Subject Santa Fe (Newsies song) E679086 entity
Predicate workTitleOfCharacter P161382 FINISHED
Object Jack Kelly’s dream song
Jack Kelly’s dream song is the heartfelt ballad “Santa Fe” from the musical Newsies, in which the character dreams of escaping New York City for a freer life in the West.
E1751459 NE FINISHED

How this triple was built (3 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: Jack Kelly’s dream song | Statement: [Santa Fe (Newsies song), workTitleOfCharacter, Jack Kelly’s dream song]
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: Jack Kelly’s dream song
Triple: [Santa Fe (Newsies song), workTitleOfCharacter, Jack Kelly’s dream song]
Generated description
Jack Kelly’s dream song is the heartfelt ballad “Santa Fe” from the musical Newsies, in which the character dreams of escaping New York City for a freer life in the West.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: workTitleOfCharacter
Context triple: [Santa Fe (Newsies song), workTitleOfCharacter, Jack Kelly’s dream song]
  • A. characterTitle
    Indicates that a character holds or is associated with a specific title, rank, or formal designation.
  • B. sourceWorkTitleCharacter
    Indicates that a character appears in, or is associated with, a specific source work identified by its title.
  • C. titleGivenByCharacter
    Indicates that a specific title is conferred upon someone or something by a particular character.
  • D. portrayedTitleCharacter
    Indicates that one entity played the main or title role character associated with another entity (such as a work or production).
  • E. protagonistTitle
    Indicates that one entity is the title or designation held by the main or central character (protagonist) of a work or narrative.
  • F. None of above. chosen

Provenance (7 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_69eeeb4f3a448190b1e94b2d4776c16e completed April 27, 2026, 4:51 a.m.
NER Named-entity recognition batch_69f620ede4f88190a98f91af97505663 completed May 2, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1229a0f3e881909aeb85701820938a completed May 23, 2026, 10:26 p.m.
NEDg Description generation batch_6a122b753ffc819099fbbe1401dabc61 completed May 23, 2026, 10:34 p.m.
NED2 Entity disambiguation (via description) batch_6a122c19dd14819093692713467547d5 completed May 23, 2026, 10:37 p.m.
PD Predicate disambiguation batch_69f611af72ac819094598dd2530d7411 completed May 2, 2026, 3:01 p.m.
PDg Predicate description generation batch_69f6125e54e0819088ee33a20efcc9e6 completed May 2, 2026, 3:03 p.m.
Created at: April 27, 2026, 6:33 a.m.