Triple

T2916874
Position Surface form Disambiguated ID Type / Status
Subject Marjorie, Countess of Carrick E78627 entity
Predicate placeOfBirth P1 FINISHED
Object Carrick E98887 NE FINISHED

How this triple was built (2 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: Carrick | Statement: [Marjorie, Countess of Carrick, placeOfBirth, Carrick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carrick
Context triple: [Marjorie, Countess of Carrick, placeOfBirth, Carrick]
  • A. Carrick chosen
    Carrick is a historic region in southwestern Scotland that served as an early power base for the medieval House of Bruce.
  • B. Carronshore
    Carronshore is a small village in Falkirk, Scotland, situated near the River Carron and historically linked to local industry and river trade.
  • C. Cardross
    Cardross is a village in Argyll and Bute, Scotland, historically notable as the place where King Robert the Bruce spent his final years and died.
  • D. Fairlie
    Fairlie is a small rural service town in New Zealand’s South Island, known as a gateway to the Mackenzie District and nearby alpine and lake attractions.
  • E. Leamouth
    Leamouth is a riverside district in East London where the River Lea meets the River Thames, known for its former industrial docks and recent waterside redevelopment.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ad8b0c2ad081909ff87050ae542bb9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad96a2bdd88190aa01c26a27f9afbd completed March 8, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0562847488190a0d6b7de99796cd9 completed March 10, 2026, 5:34 p.m.
Created at: March 8, 2026, 2:53 p.m.