Triple

T15760840
Position Surface form Disambiguated ID Type / Status
Subject Princess Milica of Serbia E382091 entity
Predicate monasticName P50298 FINISHED
Object Eugenia E328856 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: Eugenia | Statement: [Princess Milica of Serbia, monasticName, Eugenia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eugenia
Context triple: [Princess Milica of Serbia, monasticName, Eugenia]
  • A. Eugenia
    Eugenia is a station on the Mexico City Metro system, located along Line 3 in the Benito Juárez borough.
  • B. Eugenia chosen
    Eugenia is a feminine given name of Greek origin, commonly used in various European and Latin American cultures.
  • C. Sarraméa
    Sarraméa is a small inland commune in New Caledonia known for its lush mountainous landscapes and eco-tourism activities.
  • D. Acacías
    Acacías is a Colombian city in the Meta Department known for its oil industry, agriculture, and role as a gateway to the Llanos Orientales plains.
  • E. Anamirta
    Anamirta is a genus of tropical climbing plants known for species that produce toxic alkaloids historically used as fish poisons and insecticides.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e050b52c548190a0ffa4493a4eb15c completed April 16, 2026, 3 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff8774eda08190a6231b4fd5027e6f completed May 9, 2026, 7:13 p.m.
Created at: April 10, 2026, 4:47 a.m.