Triple

T7255421
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth Vassall E157705 entity
Predicate familyName P18 FINISHED
Object Vassall E157705 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: Vassall | Statement: [Elizabeth Vassall, familyName, Vassall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vassall
Context triple: [Elizabeth Vassall, familyName, Vassall]
  • A. Vassall chosen
    Vassall is an English surname historically associated with notable figures in British public life and espionage.
  • B. Lascelles
    Lascelles is a British aristocratic family name historically associated with the Earls of Harewood and close ties to the royal family.
  • C. Banagher
    Banagher is a small Irish town in County Offaly known for its historic bridge over the River Shannon and its traditional boating and angling activities.
  • D. Havelock
    Havelock is an English surname most notably associated with Sir Henry Havelock, a 19th-century British general known for his role in the Indian Rebellion of 1857.
  • E. De Vere
    De Vere is a British hospitality company known for operating a collection of country house hotels, conference venues, and event spaces across the United Kingdom.
  • 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_69c6882d81d4819085f7ff862951ee4f completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6eaa0c76c81909fe43ed6938a13ea completed March 27, 2026, 8:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7e523149481909bbc7dd88046e8b0 completed March 28, 2026, 2:26 p.m.
Created at: March 27, 2026, 2:56 p.m.