Triple

T13847951
Position Surface form Disambiguated ID Type / Status
Subject Holyhood Cemetery E332857 entity
Predicate hasNotableBurial P196 FINISHED
Object Patrick Collins
Patrick Collins was an Irish-American politician who served as mayor of Boston and a U.S. Congressman in the late 19th and early 20th centuries.
E1092562 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: Patrick Collins | Statement: [Holyhood Cemetery, hasNotableBurial, Patrick Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Patrick Collins
Context triple: [Holyhood Cemetery, hasNotableBurial, Patrick Collins]
  • A. Patrick Doherty
    Patrick Doherty was one of the unarmed civil rights marchers shot and killed by British soldiers during the Bloody Sunday massacre in Derry, Northern Ireland, in 1972.
  • B. Martin Doherty
    Martin Doherty is a Scottish musician and producer best known as a member of the synth-pop band Chvrches.
  • C. Dan Quinlivan
    Dan Quinlivan is a musician best known as a member of the experimental psychedelic and ambient ensemble Bitchin Bajas.
  • D. Patrick Dolan
    Patrick Dolan is a media executive best known for his leadership role at Newsday, a major Long Island-based newspaper.
  • E. Patrick Duggan
    Patrick Duggan is a personal name shared by multiple individuals, including figures in fields such as the arts, religion, and public service.
  • 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: Patrick Collins
Triple: [Holyhood Cemetery, hasNotableBurial, Patrick Collins]
Generated description
Patrick Collins was an Irish-American politician who served as mayor of Boston and a U.S. Congressman in the late 19th and early 20th centuries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Patrick Collins
Target entity description: Patrick Collins was an Irish-American politician who served as mayor of Boston and a U.S. Congressman in the late 19th and early 20th centuries.
  • A. Patrick Doherty
    Patrick Doherty was one of the unarmed civil rights marchers shot and killed by British soldiers during the Bloody Sunday massacre in Derry, Northern Ireland, in 1972.
  • B. Martin Doherty
    Martin Doherty is a Scottish musician and producer best known as a member of the synth-pop band Chvrches.
  • C. Dan Quinlivan
    Dan Quinlivan is a musician best known as a member of the experimental psychedelic and ambient ensemble Bitchin Bajas.
  • D. Patrick Dolan
    Patrick Dolan is a media executive best known for his leadership role at Newsday, a major Long Island-based newspaper.
  • E. Patrick Duggan
    Patrick Duggan is a personal name shared by multiple individuals, including figures in fields such as the arts, religion, and public service.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02b2a9788190b164760adec64ef6 completed April 14, 2026, 9:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69fd466ac0f08190b99dd4cdcef339c6 completed May 8, 2026, 2:11 a.m.
NEDg Description generation batch_69fd47061cb081909abe5fe35aa03ead completed May 8, 2026, 2:14 a.m.
NED2 Entity disambiguation (via description) batch_69fd4781a6788190a2174a87e00a1fd8 completed May 8, 2026, 2:16 a.m.
Created at: April 9, 2026, 10:14 p.m.