Triple

T18694766
Position Surface form Disambiguated ID Type / Status
Subject Trojans E457088 entity
Predicate ancestor P5206 FINISHED
Object Tros NE NERFINISHED

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: Tros | Statement: [Trojans, ancestor, Tros]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tros
Context triple: [Trojans, ancestor, Tros]
  • A. Tros chosen
    Tros is a figure in Greek mythology known as the eponymous founder and king of Troy, from whom the Trojans derive their name.
  • B. Trogen
    Trogen is a municipality in the canton of Appenzell Ausserrhoden in northeastern Switzerland, known for its picturesque setting and traditional Swiss architecture.
  • C. Dardanos
    Dardanos was an ancient town in the Troad region of northwestern Anatolia, known from Greek and Roman sources and associated with early Trojan legends.
  • 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 (2 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_69d8d391eb488190ac2e9abf5bf255e4 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e562e66a188190801fd95f9be26042 completed April 19, 2026, 11:19 p.m.
Created at: April 10, 2026, 11:49 a.m.