Triple

T11716474
Position Surface form Disambiguated ID Type / Status
Subject Margaret Stewart, Countess of Mar E278510 entity
Predicate associatedWithTerritory P12445 FINISHED
Object Mar
Mar is a historic earldom and region in Aberdeenshire, Scotland, long associated with one of the oldest Scottish peerage titles, the Earldom of Mar.
 E942667 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: Mar | Statement: [Margaret Stewart, Countess of Mar, associatedWithTerritory, Mar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mar
Context triple: [Margaret Stewart, Countess of Mar, associatedWithTerritory, Mar]
  • A. Mar
    Mar is an honorific ecclesiastical title used for bishops and saints in several Eastern Christian traditions, particularly within Syriac Christianity.
  • B. MA
    MA is the vehicle registration code used on license plates for the German city of Mannheim.
  • C. MA
    MA is the stock ticker symbol for Mastercard Incorporated, a leading global payments and financial services company.
  • D. MA
    MA is the two-letter ISO 3166-1 alpha-2 country code assigned to Morocco.
  • E. Mo
    Mo is a common shortened form of the given name Maureen.
  • 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: Mar
Triple: [Margaret Stewart, Countess of Mar, associatedWithTerritory, Mar]
Generated description
Mar is a historic earldom and region in Aberdeenshire, Scotland, long associated with one of the oldest Scottish peerage titles, the Earldom of Mar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mar
Target entity description: Mar is a historic earldom and region in Aberdeenshire, Scotland, long associated with one of the oldest Scottish peerage titles, the Earldom of Mar.
  • A. Mar
    Mar is an honorific ecclesiastical title used for bishops and saints in several Eastern Christian traditions, particularly within Syriac Christianity.
  • B. MA
    MA is the stock ticker symbol for Mastercard Incorporated, a leading global payments and financial services company.
  • C. MA
    MA is the vehicle registration code used on license plates for the German city of Mannheim.
  • D. MA
    MA is the two-letter ISO 3166-1 alpha-2 country code assigned to Morocco.
  • E. Mo
    Mo is a common shortened form of the given name Maureen.
  • 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_69d6aaff2ce88190b4a1e4b341ad5377 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a4c10d988190842acd824135cf15 completed April 10, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef83a9479c81909cbe63d81255a1bf completed April 27, 2026, 3:41 p.m.
NEDg Description generation batch_69ef96b0169081909ad5c5d40a006e64 completed April 27, 2026, 5:02 p.m.
NED2 Entity disambiguation (via description) batch_69efb4dad6a481909a54511b6233993b completed April 27, 2026, 7:11 p.m.
Created at: April 8, 2026, 9:40 p.m.