Triple

T22264061
Position Surface form Disambiguated ID Type / Status
Subject Lady Fairfax E550302 entity
Predicate givenName P17 FINISHED
Object Anne
Anne, known by the title Lady Fairfax, was an English noblewoman associated with the Fairfax family in the 17th century.
E1529375 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: Anne | Statement: [Lady Fairfax, givenName, Anne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anne
Context triple: [Lady Fairfax, givenName, Anne]
  • A. Anne
    Anne is the protagonist of "The Darkest Hour," around whom the film’s central conflict and emotional journey revolve.
  • B. Anne
    Anne is the middle name of American actress Julie Anne Smith, better known professionally as Julianne Moore.
  • C. Anne
    Anne is the central character in the short story "In the Gloaming," around whom the narrative’s emotional and thematic developments revolve.
  • D. Anne
    Anne is the first name of Anne Gust Brown, an American businesswoman and former First Lady of California.
  • E. Anne
    Anne is the given name of Anne Isabella Thackeray Ritchie, a 19th-century English novelist and essayist known for her works and for being the daughter of William Makepeace Thackeray.
  • 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: Anne
Triple: [Lady Fairfax, givenName, Anne]
Generated description
Anne, known by the title Lady Fairfax, was an English noblewoman associated with the Fairfax family in the 17th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Anne
Target entity description: Anne, known by the title Lady Fairfax, was an English noblewoman associated with the Fairfax family in the 17th century.
  • A. Anne
    Anne is the given name of Lady Anne Temple, a historical noblewoman likely associated with the British aristocracy.
  • B. Anne
    Anne is the given name of Anne Blunt, 15th Baroness Wentworth, a notable British aristocrat, traveler, and Arabian horse breeder.
  • C. Anne
    Anne is the given name of Lady Lucy Anne FitzGerald, an Irish noblewoman of the late 18th and early 19th centuries known for her connections to the United Irishmen movement.
  • D. Anne
    Anne Beauchamp, 16th Countess of Warwick, was a 15th-century English noblewoman and heiress whose disputed inheritance played a key role in the politics surrounding the Wars of the Roses.
  • E. Anne
    Anne was the Duchess of Brittany who twice became Queen of France in the late 15th and early 16th centuries.
  • 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_69e11e42adb8819087714772ea606709 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f141ba5c9481909e24067133918ae2 completed April 28, 2026, 11:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0acc8bb0a88190a8da7d27af71dc95 completed May 18, 2026, 8:23 a.m.
NEDg Description generation batch_6a0acd9deed081908918511b31292add completed May 18, 2026, 8:28 a.m.
NED2 Entity disambiguation (via description) batch_6a0ace5e9b948190bd4fb7092e6fb62e completed May 18, 2026, 8:31 a.m.
Created at: April 16, 2026, 8:39 p.m.