Triple

T23368998
Position Surface form Disambiguated ID Type / Status
Subject Marlow Lock E593409 entity
Predicate locatedIn P40 FINISHED
Object Marlow 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: Marlow | Statement: [Marlow Lock, locatedIn, Marlow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marlow
Context triple: [Marlow Lock, locatedIn, Marlow]
  • A. Marlow chosen
    Marlow is a historic English town on the River Thames in Buckinghamshire, known for its picturesque setting, suspension bridge, and literary associations.
  • B. Marlow
    Marlow is the brutal vampire leader and primary antagonist in the horror film "30 Days of Night."
  • C. 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."
  • D. Conrad
    Conrad is a fictional character portrayed by American actor Lucas Black, known for his roles in film and television dramas.
  • E. Conrad
    Conrad is the daring pirate hero of Lord Byron’s narrative poem “Le Corsaire,” known for his rebellious spirit and tragic romantic fate.
  • 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_69e25d2593c88190bcdf4a716a94ccb2 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a0aed374819097d38f51894bee44 completed April 29, 2026, 6:09 a.m.
Created at: April 17, 2026, 5:32 p.m.