Triple

T13750423
Position Surface form Disambiguated ID Type / Status
Subject Duke E330335 entity
Predicate givenName P17 FINISHED
Object Conrad E228611 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: Conrad | Statement: [Duke, givenName, Conrad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Conrad
Context triple: [Duke, givenName, Conrad]
  • A. Conrad
    Conrad is a character in Horace Walpole’s pioneering Gothic novel "The Castle of Otranto," whose fate helps set the story’s dark and supernatural events in motion.
  • B. Conrad chosen
    Conrad is a masculine given name of Germanic origin, commonly used in various European countries and the English-speaking world.
  • C. Conrad
    Conrad is the daring pirate hero of Lord Byron’s narrative poem “Le Corsaire,” known for his rebellious spirit and tragic romantic fate.
  • D. Conrad
    Conrad is one of the main child protagonists in Dr. Seuss's "The Cat in the Hat," known for his cautious and rule-abiding nature contrasted with the Cat's chaotic antics.
  • E. Charles Marlow
    Charles Marlow is the introspective sailor and storyteller who serves as the primary narrator in several of Joseph Conrad’s works, most notably "Heart of Darkness."
  • 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_69d81c573f288190aa2403d484fa3d49 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02148c208190a882927905a861a6 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a8560614819085958205637f3863 completed May 3, 2026, 7:56 p.m.
Created at: April 9, 2026, 10:08 p.m.