Triple

T9488295
Position Surface form Disambiguated ID Type / Status
Subject Fresnes E228817 entity
Predicate nearbyCity P350 FINISHED
Object Antony E67385 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: Antony | Statement: [Fresnes, nearbyCity, Antony]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Antony
Context triple: [Fresnes, nearbyCity, Antony]
  • A. Antony chosen
    Antony is a suburban commune in the southern outskirts of Paris, France, known for its residential character and connection to central Paris via the RER B commuter rail line.
  • B. Antony
    Antony is the given name of Antony Armstrong-Jones, 1st Earl of Snowdon, a British photographer and former husband of Princess Margaret.
  • C. Mark Antony
    Mark Antony was a prominent Roman general and statesman, ally of Julius Caesar and lover of Cleopatra, whose power struggle with Octavian culminated in his defeat at the Battle of Actium.
  • D. Antonius
    Antonius is an ancient Roman family name (nomen gentilicium) most famously borne by the general and politician Mark Antony (Marcus Antonius).
  • E. Marcus Antonius Primus
    Marcus Antonius Primus was a 1st-century Roman general and senator best known for his decisive role in supporting Vespasian during the Year of the Four Emperors.
  • 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_69ca847424f081908180305555139f7a completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd80c443b88190968d2092a73e1ee4 completed April 1, 2026, 8:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1af37e78081909683ce5359a8eb0e completed April 5, 2026, 12:39 a.m.
Created at: March 30, 2026, 7:55 p.m.