Triple

T19083716
Position Surface form Disambiguated ID Type / Status
Subject Clytius E467090 entity
Predicate residence P75 FINISHED
Object Troy 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: Troy | Statement: [Clytius, residence, Troy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Troy
Context triple: [Clytius, residence, Troy]
  • A. Troy
    Troy is a 2004 epic historical war film loosely based on Homer's Iliad, depicting the legendary conflict between the Greeks and Trojans.
  • B. Troy
    Troy is a small city in southeastern Alabama known for being the home of Troy University and its vibrant college-town atmosphere.
  • C. Troy chosen
    Troy is the legendary ancient city in Asia Minor that was the focal point of the Trojan War in Greek and Roman mythology.
  • D. Troy
    Troy is a masculine given name of ancient origin, famously borne by former NFL quarterback Troy Aikman.
  • E. Troy
    "Troy" is a powerful early single by Irish singer-songwriter Sinéad O’Connor, known for its intense emotional delivery and poetic lyrics.
  • 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_69d8dd04f4488190b1121cc53ef2bfd6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e34600f88190bd96bcc2c5c08d14 completed April 20, 2026, 8:26 a.m.
Created at: April 10, 2026, 12:04 p.m.