Triple

T2267884
Position Surface form Disambiguated ID Type / Status
Subject Andrew Marr E50189 entity
Predicate familyName P18 FINISHED
Object Marr
Marr is a Scottish surname most prominently associated with British journalist and broadcaster Andrew Marr.
 E249903 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: Marr | Statement: [Andrew Marr, familyName, Marr]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marr
Context triple: [Andrew Marr, familyName, Marr]
  • A. Martz
    Martz is a surname most notably associated with Mike Martz, an American football coach known for his innovative offensive strategies in the NFL.
  • B. Maynard
    Maynard is the middle name of the influential British economist John Maynard Keynes, a key figure in modern macroeconomic theory.
  • C. Murch
    Murch is the surname of Walter Murch, the acclaimed American film editor and sound designer known for his work on films like "Apocalypse Now" and "The English Patient."
  • D. Maran
    Maran is an honorific title most famously associated with Rabbi Yosef Karo, the preeminent 16th-century halachic authority and author of the Shulchan Aruch.
  • E. Millar
    Millar is a surname and variant spelling of Miller, commonly found in English-speaking countries.
  • 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: Marr
Triple: [Andrew Marr, familyName, Marr]
Generated description
Marr is a Scottish surname most prominently associated with British journalist and broadcaster Andrew Marr.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marr
Target entity description: Marr is a Scottish surname most prominently associated with British journalist and broadcaster Andrew Marr.
  • A. Martz
    Martz is a surname most notably associated with Mike Martz, an American football coach known for his innovative offensive strategies in the NFL.
  • B. Maynard
    Maynard is the middle name of the influential British economist John Maynard Keynes, a key figure in modern macroeconomic theory.
  • C. Murch
    Murch is the surname of Walter Murch, the acclaimed American film editor and sound designer known for his work on films like "Apocalypse Now" and "The English Patient."
  • D. Maran
    Maran is an honorific title most famously associated with Rabbi Yosef Karo, the preeminent 16th-century halachic authority and author of the Shulchan Aruch.
  • E. Millar
    Millar is a surname and variant spelling of Miller, commonly found in English-speaking countries.
  • 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_69a88b01e0048190ba96431b5f990ba9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc1bbb49c8190822c7d809375e879 completed March 7, 2026, 6:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71d70e488190a2f8276dd7a7bf9e completed March 9, 2026, 7:08 a.m.
NEDg Description generation batch_69ae7470e3ac8190ac6e8f7cd10a4262 completed March 9, 2026, 7:19 a.m.
NED2 Entity disambiguation (via description) batch_69ae751895808190aac33870d80aab55 completed March 9, 2026, 7:22 a.m.
Created at: March 4, 2026, 7:48 p.m.