Triple

T8687387
Position Surface form Disambiguated ID Type / Status
Subject Into the Deep: A Memoir From the Man Who Found Titanic E206195 entity
Predicate aboutVessel P56823 FINISHED
Object RMS Titanic E80262 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: RMS Titanic | Statement: [Into the Deep: A Memoir From the Man Who Found Titanic, aboutVessel, RMS Titanic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RMS Titanic
Context triple: [Into the Deep: A Memoir From the Man Who Found Titanic, aboutVessel, RMS Titanic]
  • A. RMS Titanic chosen
    RMS Titanic was a British Olympic-class ocean liner that tragically sank on its maiden voyage in 1912 after striking an iceberg, becoming one of the most famous maritime disasters in history.
  • B. RMS Olympic
    RMS Olympic was a British Olympic-class ocean liner of the White Star Line, best known as the near-identical sister ship of the Titanic and for her long, successful service career.
  • C. RMS Lusitania
    RMS Lusitania was a British ocean liner famously sunk by a German U-boat in 1915 during World War I, an event that significantly influenced public opinion against Germany.
  • D. HMHS Britannic
    HMHS Britannic was a British White Star Line ocean liner, sister ship to the Titanic and Olympic, that served as a World War I hospital ship before sinking in the Aegean Sea in 1916.
  • E. Lusitania
    Lusitania was an ancient Roman province on the western Iberian Peninsula, roughly corresponding to much of modern Portugal and part of western Spain.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: aboutVessel
Context triple: [Into the Deep: A Memoir From the Man Who Found Titanic, aboutVessel, RMS Titanic]
  • A. featuresVessel chosen
    Indicates that one entity includes, presents, or prominently displays a particular vessel as part of its composition, content, or configuration.
  • B. hasVessel
    Indicates that one entity possesses, uses, or is associated with a particular vessel (such as a container, ship, or transport medium) in the context of the described relationship or action.
  • C. hasVesselType
    Indicates that an entity is associated with or classified by a specific type of vessel (e.g., ship, boat, or container).
  • D. governmentVessel
    Indicates that the vessel is owned, operated, or officially designated for use by a government or governmental authority.
  • E. operatesVessel
    Indicates that an agent is responsible for controlling, managing, or running the operation of a vessel.
  • 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_69ca835481fc819084e33d3bc883bfa6 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5731cf08819082e0cbe0975b70bb completed March 31, 2026, 11:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf88c11f788190b7ab86fe8cf278bd completed April 3, 2026, 9:30 a.m.
PD Predicate disambiguation batch_69cc4569f9048190b9c86b4c81103d35 completed March 31, 2026, 10:06 p.m.
Created at: March 30, 2026, 6:33 p.m.