Triple

T19012203
Position Surface form Disambiguated ID Type / Status
Subject Herleva E465254 entity
Predicate alternativeName P39 FINISHED
Object Harlette
Harlette is a historical figure better known as Herleva, traditionally regarded as the mother of William the Conqueror.
E1354035 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: Harlette | Statement: [Herleva, alternativeName, Harlette]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harlette
Context triple: [Herleva, alternativeName, Harlette]
  • A. Sybille
    Sybille was a French frigate that took part in the early 19th-century naval engagement known as the Battle of San Domingo.
  • B. Bethia
    Bethia was the original name of the British merchant vessel that was later purchased by the Royal Navy and renamed HMS Bounty, famed for the 1789 mutiny.
  • C. Leonila
    Leonila is a feminine given name commonly used in the Philippines and other Spanish-influenced cultures.
  • D. Pauletta
    Pauletta is a feminine given name, typically considered a diminutive or variant of Paula or Pauline.
  • E. Horatia
    Horatia is a feminine given name most notably borne by Horatia Nelson, the daughter of British naval hero Admiral Horatio Nelson and Emma Hamilton.
  • 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: Harlette
Triple: [Herleva, alternativeName, Harlette]
Generated description
Harlette is a historical figure better known as Herleva, traditionally regarded as the mother of William the Conqueror.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Harlette
Target entity description: Harlette is a historical figure better known as Herleva, traditionally regarded as the mother of William the Conqueror.
  • A. Sybille
    Sybille was a French frigate that took part in the early 19th-century naval engagement known as the Battle of San Domingo.
  • B. Bethia
    Bethia was the original name of the British merchant vessel that was later purchased by the Royal Navy and renamed HMS Bounty, famed for the 1789 mutiny.
  • C. Leonila
    Leonila is a feminine given name commonly used in the Philippines and other Spanish-influenced cultures.
  • D. Pauletta
    Pauletta is a feminine given name, typically considered a diminutive or variant of Paula or Pauline.
  • E. Horatia
    Horatia is a feminine given name most notably borne by Horatia Nelson, the daughter of British naval hero Admiral Horatio Nelson and Emma Hamilton.
  • 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6a9bac8819093f9af57000667b0 completed April 20, 2026, 7:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05b467a8cc81909106355f3b011ae3 completed May 14, 2026, 11:39 a.m.
NEDg Description generation batch_6a05b706025c8190aed7945dad186ba5 completed May 14, 2026, 11:50 a.m.
NED2 Entity disambiguation (via description) batch_6a05b7e153948190b19a6ad3ffff2aba completed May 14, 2026, 11:54 a.m.
Created at: April 10, 2026, 12:02 p.m.