Triple

T23099771
Position Surface form Disambiguated ID Type / Status
Subject Tom Pullings E575992 entity
Predicate appearsIn P795 FINISHED
Object The Wine-Dark Sea 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: The Wine-Dark Sea | Statement: [Tom Pullings, appearsIn, The Wine-Dark Sea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Wine-Dark Sea
Context triple: [Tom Pullings, appearsIn, The Wine-Dark Sea]
  • A. The Wine-Dark Sea chosen
    The Wine-Dark Sea is a historical naval novel by Patrick O’Brian, following Captain Jack Aubrey and physician-intelligence agent Stephen Maturin through complex seafaring adventures during the Napoleonic Wars.
  • B. Les Phocéens
    Les Phocéens is the traditional nickname for Olympique de Marseille, referencing the ancient Greek settlers of the city of Marseille (Phocaea).
  • C. Mares of Diomedes
    The Mares of Diomedes are man-eating horses from Greek mythology that Heracles was tasked with capturing as one of his Twelve Labors.
  • D. Omeros
    Omeros is an epic poem by Derek Walcott that reimagines Homeric themes in a Caribbean setting, blending history, myth, and postcolonial reflection.
  • E. Riviera di Ulisse
    Riviera di Ulisse is a scenic coastal area in southern Lazio, Italy, famed for its sandy beaches, rocky promontories, and historical sites linked to the legends of Ulysses.
  • 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_69e245c060b48190a9bd61a47a16db17 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18de81060819084ab618f05aae583 completed April 29, 2026, 4:49 a.m.
Created at: April 17, 2026, 3:58 p.m.