Triple

T1236698
Position Surface form Disambiguated ID Type / Status
Subject Bibliotheca E26563 entity
Predicate coversTopic P380 FINISHED
Object Trojan cycle E85748 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: Trojan cycle | Statement: [Bibliotheca, coversTopic, Trojan cycle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trojan cycle
Context triple: [Bibliotheca, coversTopic, Trojan cycle]
  • A. Trojan cycle chosen
    The Trojan cycle is a collection of ancient Greek epic poems that narrate the full saga of the Trojan War and its aftermath beyond what is told in Homer’s Iliad and Odyssey.
  • B. Capture of Cerberus
    Capture of Cerberus is the twelfth and final labor of the Greek hero Heracles, in which he must descend into the Underworld and bring back Hades’ three-headed guard dog alive.
  • C. Troy
    Troy is a small city in southeastern Alabama known for being the home of Troy University and its vibrant college-town atmosphere.
  • D. Troy
    Troy is a historic city in eastern New York State, known for its 19th-century architecture and role in the Industrial Revolution as a major manufacturing center.
  • E. Troy
    Troy is a 2004 epic historical war film loosely based on Homer's Iliad, depicting the legendary conflict between the Greeks and Trojans.
  • 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_69a4948571c88190a9191e451e6035fd completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4bf17e0bc8190a066561e6b629fc0 completed March 1, 2026, 10:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac8a18b0f48190adb5b2c1e2a1019a completed March 7, 2026, 8:27 p.m.
Created at: March 1, 2026, 7:47 p.m.