Triple

T10121779
Position Surface form Disambiguated ID Type / Status
Subject Paul Sarossy E223307 entity
Predicate workedOn P3 FINISHED
Object Reign E299564 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: Reign | Statement: [Paul Sarossy, workedOn, Reign]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Reign
Context triple: [Paul Sarossy, workedOn, Reign]
  • A. Reign
    Reign is a professional American women's soccer team competing in the National Women's Soccer League and based in the Seattle metropolitan area.
  • B. La Reina
    La Reina is a residential and commercial commune in eastern Santiago, Chile, known for its quiet neighborhoods and proximity to the Andes foothills.
  • C. The Spanish Princess
    The Spanish Princess is a historical drama television series that chronicles the life of Catherine of Aragon and the political intrigue of the Tudor court in early 16th-century England.
  • D. Princess Regent
    A Princess Regent is a female royal who temporarily rules a kingdom or principality in place of the reigning monarch, typically due to the monarch’s minority, absence, or incapacity.
  • E. The Virgin Queen chosen
    The Virgin Queen is a British historical drama television series that chronicles the life and reign of Queen Elizabeth I of England.
  • 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_69ca8422047c81909d66b717b8b18cf3 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd26846b8819098594bf211920eb2 completed April 2, 2026, 2:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cc493db88190b3b09a77b82b3cc9 completed April 5, 2026, 8:55 p.m.
Created at: March 30, 2026, 9:04 p.m.