Triple

T9986150
Position Surface form Disambiguated ID Type / Status
Subject Henry Seymour Conway E196571 entity
Predicate spouse P13 FINISHED
Object Caroline Campbell E179136 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: Caroline Campbell | Statement: [Henry Seymour Conway, spouse, Caroline Campbell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caroline Campbell
Context triple: [Henry Seymour Conway, spouse, Caroline Campbell]
  • A. Caroline Campbell chosen
    Caroline Campbell was an 18th-century British noblewoman who became Countess of Dalkeith and later Duchess of Buccleuch through her marriage into the influential Scott family.
  • B. Caroline Thompson
    Caroline Thompson is an American screenwriter and director best known for her work on darkly whimsical films such as Edward Scissorhands, The Nightmare Before Christmas, and Corpse Bride.
  • C. Caroline Ridington
    Caroline Ridington was the wife of pioneering American film director and early cinema innovator Edwin S. Porter.
  • D. Caroline Ross
    Caroline Ross is a film editor known for her work on the science fiction movie "Starship Troopers."
  • E. Caroline Pearson
    Caroline Pearson was the wife of English postal reformer Rowland Hill, known primarily through her association with his pioneering work on the modern postal system.
  • 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_69ca82efbce081908179b4b9c65096eb completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdc79af13c81909349ae0b0d5da946 completed April 2, 2026, 1:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cb77b51481908af779b8ecacc3f1 completed April 5, 2026, 8:52 p.m.
Created at: March 30, 2026, 8:49 p.m.