Triple

T2103193
Position Surface form Disambiguated ID Type / Status
Subject John Keats E37134 entity
Predicate notableWork P4 FINISHED
Object Hyperion E105134 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: Hyperion | Statement: [John Keats, notableWork, Hyperion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hyperion
Context triple: [John Keats, notableWork, Hyperion]
  • A. Hyperion
    Hyperion is one of Saturn’s larger, irregularly shaped moons, known for its chaotic rotation and sponge-like, heavily cratered surface.
  • B. Hyperion
    Hyperion is a romantic travelogue novel by Henry Wadsworth Longfellow that blends fiction, philosophy, and lyrical descriptions of Germany.
  • C. Hyperion chosen
    Hyperion is a Titan from Greek mythology associated with heavenly light and often regarded as a primordial god linked to the sun and celestial bodies.
  • D. Ananke
    Ananke is the ancient Greek personification of inevitability, compulsion, and necessity, often regarded as a primordial force that even the gods must obey.
  • E. Adrestia
    Adrestia is a lesser-known Greek goddess associated with revolt, retribution, and the balance between war and peace.
  • 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_69a8861828948190924aa30c08806b3a completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abbabe1e9081908ea66c5406e2f1d9 completed March 7, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae3068189c81909cf76fd1fc2a0fe6 completed March 9, 2026, 2:28 a.m.
Created at: March 4, 2026, 7:43 p.m.