Triple

T22993230
Position Surface form Disambiguated ID Type / Status
Subject Cecilie E572111 entity
Predicate derivedFrom P909 FINISHED
Object Caecilia NE NERFINISHED

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: Caecilia | Statement: [Cecilie, derivedFrom, Caecilia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caecilia
Context triple: [Cecilie, derivedFrom, Caecilia]
  • A. Caecilia chosen
    Caecilia is a Latin feminine given name, historically associated with the Roman family name Caecilius and later with the Christian saint Cecilia.
  • B. Dioclea
    Dioclea is a medieval Balkan principality, also known as Duklja, that was centered in what is now Montenegro.
  • C. Callirrhoe
    Callirrhoe is a figure in Greek mythology, often depicted as an Oceanid or nymph associated with rivers and springs.
  • D. Hersilia
    Hersilia is a figure from Roman mythology, traditionally known as the wife of Romulus and a central mediator in the legendary conflict between the Romans and the Sabine women.
  • E. Rhynchotus
    Rhynchotus is a genus of South American tinamous, ground-dwelling birds known for their plump bodies, short wings, and secretive behavior in grassland and scrub habitats.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245b535808190adef8a9df3c584db completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f182f017a88190b02d0649a3af5d99 completed April 29, 2026, 4:02 a.m.
Created at: April 17, 2026, 3:50 p.m.