Triple

T1921625
Position Surface form Disambiguated ID Type / Status
Subject Working on a Dream E40136 entity
Predicate hasTrack P3284 FINISHED
Object Good Eye
"Good Eye" is a song by Bruce Springsteen featured on his 2009 rock album *Working on a Dream*.
E217026 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: Good Eye | Statement: [Working on a Dream, hasTrack, Good Eye]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Good Eye
Context triple: [Working on a Dream, hasTrack, Good Eye]
  • A. Doctor My Eyes
    "Doctor My Eyes" is a 1972 soft rock song by Jackson Browne, known for its introspective lyrics and distinctive piano-driven melody.
  • B. The Eyeopener
    The Eyeopener is an independent student-run newspaper serving the Toronto Metropolitan University community with campus news, commentary, and features.
  • C. Red Eye
    Red Eye is a 2005 psychological thriller film in which Cillian Murphy plays a charming but menacing terrorist who coerces a hotel manager during a tense overnight flight.
  • D. Blink
    Blink is an open-source web browser engine developed primarily by Google and used in several major browsers to render web pages.
  • E. Big Eyes
    Big Eyes is a 2014 biographical drama film directed by Tim Burton that tells the story of painter Margaret Keane and the legal battle over the credit for her distinctive big-eyed children paintings.
  • 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: Good Eye
Triple: [Working on a Dream, hasTrack, Good Eye]
Generated description
"Good Eye" is a song by Bruce Springsteen featured on his 2009 rock album *Working on a Dream*.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Good Eye
Target entity description: "Good Eye" is a song by Bruce Springsteen featured on his 2009 rock album *Working on a Dream*.
  • A. Doctor My Eyes
    "Doctor My Eyes" is a 1972 soft rock song by Jackson Browne, known for its introspective lyrics and distinctive piano-driven melody.
  • B. The Eyeopener
    The Eyeopener is an independent student-run newspaper serving the Toronto Metropolitan University community with campus news, commentary, and features.
  • C. Red Eye
    Red Eye is a 2005 psychological thriller film in which Cillian Murphy plays a charming but menacing terrorist who coerces a hotel manager during a tense overnight flight.
  • D. Blink
    Blink is an open-source web browser engine developed primarily by Google and used in several major browsers to render web pages.
  • E. Big Eyes
    Big Eyes is a 2014 biographical drama film directed by Tim Burton that tells the story of painter Margaret Keane and the legal battle over the credit for her distinctive big-eyed children paintings.
  • 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_69a8864298748190a2f2fd34f7ef8d77 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb233011881908736523d36f01b0c completed March 7, 2026, 5:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69adf3e458e8819098ea1c2d5598f890 completed March 8, 2026, 10:10 p.m.
NEDg Description generation batch_69adf4cd91008190ada815601d9f76b4 completed March 8, 2026, 10:14 p.m.
NED2 Entity disambiguation (via description) batch_69adf5681ea88190979237322fd2785b completed March 8, 2026, 10:17 p.m.
Created at: March 4, 2026, 7:35 p.m.