Triple

T22744976
Position Surface form Disambiguated ID Type / Status
Subject Frank Martin E562523 entity
Predicate familyName P18 FINISHED
Object Martin
Martin is a common European surname of Latin origin, widely borne by notable figures across politics, sports, arts, and religion.
E214356 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: Martin | Statement: [Frank Martin, familyName, Martin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martin
Context triple: [Frank Martin, familyName, Martin]
  • A. Martin
    Martin is the central protagonist of the 1991 psychological thriller film "Proof," around whom the story’s exploration of trust, perception, and human connection revolves.
  • B. Martin
    Martin is the middle name of Roswell Field, an American lawyer best known for his involvement in the Dred Scott case.
  • C. Martin
    Martin is the central protagonist of the work "Newness," around whom the story’s themes and events primarily revolve.
  • D. Martin
    Martin "Buggsy" Goldstein was an American mobster and contract killer associated with Murder, Inc. in the 1930s and 1940s.
  • E. Martin
    Martin is the central protagonist of the story "Stake Land," a post-apocalyptic horror narrative featuring a vampire-ravaged America.
  • 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: Martin
Triple: [Frank Martin, familyName, Martin]
Generated description
Martin is a common European surname of Latin origin, widely borne by notable figures across politics, sports, arts, and religion.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Martin
Target entity description: Martin is a common European surname of Latin origin, widely borne by notable figures across politics, sports, arts, and religion.
  • A. Martin chosen
    Martin is a common surname of European origin, widely borne by individuals across many countries and cultures.
  • B. Martin
    Martin is a masculine given name of Latin origin, commonly used in many European languages.
  • C. Martin
    Martin is the given name of Martin Luther King Jr., the prominent American civil rights leader and Baptist minister who advocated nonviolent resistance to racial segregation.
  • D. Martin
    Martin is the given name of Martin Luther the Younger, a 16th-century German theologian and the son of Protestant Reformation leader Martin Luther.
  • E. Martin
    Martin is the given name of Martin Delany, a prominent 19th-century African American abolitionist, writer, and one of the first Black field officers in the U.S. Army.
  • F. None of above.

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_69e245513a5c81908d5cb471b4fc429d completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f179b563e481908804d07fca1777b9 completed April 29, 2026, 3:23 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b8fd41bcc81909e23e380bf834ca5 completed May 18, 2026, 10:16 p.m.
NEDg Description generation batch_6a0b93d4b8e08190a0542ffc42f12814 completed May 18, 2026, 10:33 p.m.
NED2 Entity disambiguation (via description) batch_6a0b94bbb9c88190a7ab0937d1b398a5 completed May 18, 2026, 10:37 p.m.
Created at: April 17, 2026, 3:23 p.m.