Triple

T4727279
Position Surface form Disambiguated ID Type / Status
Subject Herleva of Falaise E104915 entity
Predicate alternativeName P39 FINISHED
Object Arlette
Arlette, also known as Herleva of Falaise, was the mother of William the Conqueror and a key figure in the early life of the first Norman king of England.
 E466084 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: Arlette | Statement: [Herleva of Falaise, alternativeName, Arlette]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Arlette
Context triple: [Herleva of Falaise, alternativeName, Arlette]
  • A. Antoinette
    Antoinette is the birth name of Princess Muna al-Hussein, the British-born mother of King Abdullah II of Jordan.
  • B. Antoinette
    Antoinette is a feminine given name of French origin, historically associated with nobility and later borne by various notable figures in the arts and public life.
  • C. Martine
    Martine is a feminine given name commonly used in French- and English-speaking countries.
  • D. Aline
    Aline is a feminine given name of French origin, commonly used in various cultures and languages.
  • E. Françoise
    Françoise is the given name of Louise de La Vallière, a 17th-century French noblewoman best known as a mistress of King Louis XIV.
  • 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: Arlette
Triple: [Herleva of Falaise, alternativeName, Arlette]
Generated description
Arlette, also known as Herleva of Falaise, was the mother of William the Conqueror and a key figure in the early life of the first Norman king of England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Arlette
Target entity description: Arlette, also known as Herleva of Falaise, was the mother of William the Conqueror and a key figure in the early life of the first Norman king of England.
  • A. Antoinette
    Antoinette is a feminine given name of French origin, historically associated with nobility and later borne by various notable figures in the arts and public life.
  • B. Antoinette
    Antoinette is the birth name of Princess Muna al-Hussein, the British-born mother of King Abdullah II of Jordan.
  • C. Martine
    Martine is a feminine given name commonly used in French- and English-speaking countries.
  • D. Aline
    Aline is a feminine given name of French origin, commonly used in various cultures and languages.
  • E. Françoise
    Françoise is the given name of Louise de La Vallière, a 17th-century French noblewoman best known as a mistress of King Louis XIV.
  • 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_69bd43ed84648190ae0b7ee8e8d00482 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd644872508190887043de6c30c3da completed March 20, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be3a0739a88190aefc952d9d9b39e2 completed March 21, 2026, 6:26 a.m.
NEDg Description generation batch_69be3bee50708190938feae0a3ddeb48 completed March 21, 2026, 6:34 a.m.
NED2 Entity disambiguation (via description) batch_69be3cd64d0c8190b007e9f027185225 completed March 21, 2026, 6:38 a.m.
Created at: March 20, 2026, 1:18 p.m.