Triple

T7694009
Position Surface form Disambiguated ID Type / Status
Subject Dr. Igor E174323 entity
Predicate conductsExperimentOn P31889 FINISHED
Object Veronika unclear NED1 NE FINISHED

How this triple was built (3 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: Veronika | Statement: [Dr. Igor, conductsExperimentOn, Veronika]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Veronika
Context triple: [Dr. Igor, conductsExperimentOn, Veronika]
  • A. Veronika
    Veronika is the troubled young protagonist of Paulo Coelho's novel "Veronika Decides to Die," whose suicide attempt leads her to a transformative stay in a mental institution.
  • B. Vera
    Vera is a memorable supporting character from the 1989 Eddie Murphy film "Harlem Nights," known for her tough, comedic persona.
  • C. Vera
    Vera Rubin was an influential American astronomer whose pioneering work on galaxy rotation curves provided key evidence for the existence of dark matter.
  • D. Vera
    Vera is a feminine given name of Slavic origin, commonly used in Russian and other Eastern European cultures, meaning "faith."
  • E. Milena
    Milena is the birth name of actress Mila Kunis, a Ukrainian-born American performer known for roles in "That '70s Show" and "Black Swan."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: conductsExperimentOn
Context triple: [Dr. Igor, conductsExperimentOn, Veronika]
  • A. experimentedOn chosen
    Indicates that one entity conducted experiments or tests on another entity as the subject of investigation.
  • B. parallelExperiment
    Indicates that one experiment is conducted alongside another under comparable conditions, typically for simultaneous testing or comparison.
  • C. notableExperiment
    Indicates that an entity is recognized for having conducted or been the subject of a particularly important or influential experiment.
  • D. hasTypeOfExperiment
    Indicates that an experiment is associated with or classified under a specific type or category of experiment.
  • E. experiment
    Indicates that an entity conducts, participates in, or is the subject of a controlled test or trial to observe outcomes or validate hypotheses.
  • F. None of above.

Provenance (4 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_69c6995966348190939e6c37ba272c06 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c706d1f0208190bc5b695aa5736244 completed March 27, 2026, 10:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8c7b8b1fc8190a3c81c0ee018bb97 completed March 29, 2026, 6:33 a.m.
PD Predicate disambiguation batch_69c70163dea88190ae729df50e63dfd7 completed March 27, 2026, 10:15 p.m.
Created at: March 27, 2026, 4:02 p.m.