Triple

T4648107
Position Surface form Disambiguated ID Type / Status
Subject Trojan War E102221 entity
Predicate hasMotif P2366 FINISHED
Object Trojan Horse E403276 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 Horse | Statement: [Trojan War, hasMotif, Trojan Horse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trojan Horse
Context triple: [Trojan War, hasMotif, Trojan Horse]
  • A. Trojan Horse chosen
    The Trojan Horse is a legendary deceptive wooden structure used by the Greeks to infiltrate and ultimately conquer the city of Troy in ancient Greek mythology.
  • B. Trojan
    Trojan is the athletics nickname and mascot representing the sports teams of Trinidad State College.
  • C. Trojan cycle
    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.
  • D. Trojans
    The Trojans are the athletic teams representing the University of Southern California in collegiate sports.
  • E. Cyber Pearl
    Cyber Pearl is a prominent commercial office complex in Hyderabad’s HITEC City, known for housing numerous IT and technology companies.
  • 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_69bd43d71a308190afea7280841b0de8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd62feeb6c8190a7807c37e9a6fa00 completed March 20, 2026, 3:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfadfe8b4819088a5fb1565bbe94a completed March 21, 2026, 1:56 a.m.
Created at: March 20, 2026, 1:14 p.m.