Triple

T16523069
Position Surface form Disambiguated ID Type / Status
Subject Helenus E401367 entity
Predicate twin P2516 FINISHED
Object Cassandra E84806 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: Cassandra | Statement: [Helenus, twin, Cassandra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cassandra
Context triple: [Helenus, twin, Cassandra]
  • A. Cassandra
    "Cassandra" is a song by Florence + The Machine from their album "Dance Fever," blending mythic lyricism with dramatic, atmospheric indie rock.
  • B. Cassandra chosen
    Cassandra is a figure from Greek mythology, a Trojan princess and prophetess cursed to utter true prophecies that no one would ever believe.
  • C. Cassandra
    "Cassandra" is a song by Taylor Swift from her album *The Tortured Poets Department*, likely exploring themes of foresight, disbelief, and emotional turmoil inspired by the mythological figure Cassandra.
  • D. Cassandra
    Cassandra is a highly scalable, distributed NoSQL database designed for handling large amounts of data across many commodity servers with no single point of failure.
  • E. Cassandane
    Cassandane was a Persian noblewoman of the Achaemenid dynasty, best known as the queen consort of Cyrus the Great and mother of his successor Cambyses II.
  • 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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e8158cc8190aa77c6d37bd7ec76 completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0067a7616c8190af486bef3331e115 completed May 10, 2026, 11:10 a.m.
Created at: April 10, 2026, 5:14 a.m.