Triple

T23134320
Position Surface form Disambiguated ID Type / Status
Subject Princess Delphine of Belgium E577266 entity
Predicate hasChild P369 FINISHED
Object Oscar O’Hare
Oscar O’Hare is a member of the Belgian royal family as the son of Princess Delphine of Belgium.
 E1574537 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: Oscar O’Hare | Statement: [Princess Delphine of Belgium, hasChild, Oscar O’Hare]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Oscar O’Hare
Context triple: [Princess Delphine of Belgium, hasChild, Oscar O’Hare]
  • A. Richard O'Hare
    Richard O'Hare was the son of prominent American socialist and antiwar activist Kate Richards O'Hare.
  • B. Donald O’Brien
    Donald O’Brien was an Irish-born actor best known for his villainous and character roles in Italian genre cinema, particularly Spaghetti Westerns and horror films.
  • C. George O’Brien
    George O’Brien was an American film actor best known as a leading man in silent-era Westerns and adventure films who successfully transitioned into sound cinema.
  • D. Pat O’Brien
    Pat O’Brien is an American sportscaster and television host best known for his long-running work on programs like Access Hollywood and The Insider.
  • E. Pat O’Brien
    Pat O’Brien was an American film and stage actor best known for his prolific work in Hollywood from the 1930s to the 1950s, often portraying fast-talking priests, cops, and authority figures.
  • 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: Oscar O’Hare
Triple: [Princess Delphine of Belgium, hasChild, Oscar O’Hare]
Generated description
Oscar O’Hare is a member of the Belgian royal family as the son of Princess Delphine of Belgium.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Oscar O’Hare
Target entity description: Oscar O’Hare is a member of the Belgian royal family as the son of Princess Delphine of Belgium.
  • A. Richard O'Hare
    Richard O'Hare was the son of prominent American socialist and antiwar activist Kate Richards O'Hare.
  • B. Donald O’Brien
    Donald O’Brien was an Irish-born actor best known for his villainous and character roles in Italian genre cinema, particularly Spaghetti Westerns and horror films.
  • C. George O’Brien
    George O’Brien was an American film actor best known as a leading man in silent-era Westerns and adventure films who successfully transitioned into sound cinema.
  • D. Pat O’Brien
    Pat O’Brien was an American film and stage actor best known for his prolific work in Hollywood from the 1930s to the 1950s, often portraying fast-talking priests, cops, and authority figures.
  • E. Pat O’Brien
    Pat O’Brien is an American sportscaster and television host best known for his long-running work on programs like Access Hollywood and The Insider.
  • 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_69e245f7b0e481909c473ff4e6a54e2c completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18e8ab9b08190969984f8c4494b0f completed April 29, 2026, 4:52 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c308901088190a3dd91561a5c123f completed May 19, 2026, 9:42 a.m.
NEDg Description generation batch_6a0c3468ecf48190ae05d776b6b472c6 completed May 19, 2026, 9:59 a.m.
NED2 Entity disambiguation (via description) batch_6a0c34b344248190a6f1b34dede10db1 completed May 19, 2026, 10 a.m.
Created at: April 17, 2026, 4 p.m.