Triple

T17300423
Position Surface form Disambiguated ID Type / Status
Subject Lady Godiva E420024 entity
Predicate residence P75 FINISHED
Object Mercia E34551 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: Mercia | Statement: [Lady Godiva, residence, Mercia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mercia
Context triple: [Lady Godiva, residence, Mercia]
  • A. Mercia chosen
    Mercia was one of the major Anglo-Saxon kingdoms of early medieval England, centered in the English Midlands and prominent from the 7th to 9th centuries.
  • B. Cenred of Mercia
    Cenred of Mercia was an early 8th-century king of the Anglo-Saxon kingdom of Mercia, known for consolidating its power in central England.
  • C. Ine of Wessex
    Ine of Wessex was an early 8th-century Anglo-Saxon king noted for consolidating the kingdom of Wessex and issuing one of the earliest surviving English law codes.
  • D. Kings of Mercia
    Kings of Mercia were the monarchs who ruled the Anglo-Saxon kingdom of Mercia, one of the most powerful early medieval English realms.
  • E. Kingdom of Wessex
    The Kingdom of Wessex was an early medieval Anglo-Saxon realm in southern England that rose to dominance over other English kingdoms and laid the foundations for a unified English state.
  • 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_69d886db32608190a61e18862c5a8af6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e438f9e5ac8190ba0b5820790112d9 completed April 19, 2026, 2:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0180dc929c819096a7a5dc81e5b6ef completed May 11, 2026, 7:10 a.m.
Created at: April 10, 2026, 5:41 a.m.