Triple

T8012199
Position Surface form Disambiguated ID Type / Status
Subject Troy Perkins E186520 entity
Predicate givenName P17 FINISHED
Object Troy
Troy is an ancient city in northwestern Anatolia, famed as the setting of the Trojan War in Greek mythology and Homer’s epic poems.
 E112533 NE FINISHED

How this triple was built (4 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: [Troy Perkins, givenName, Troy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Troy
Context triple: [Troy Perkins, givenName, Troy]
  • A. Troy
    Troy is a small city in southeastern Alabama known for being the home of Troy University and its vibrant college-town atmosphere.
  • B. 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.
  • C. Troy
    Troy is a 2004 epic historical war film loosely based on Homer's Iliad, depicting the legendary conflict between the Greeks and Trojans.
  • D. Troy
    Troy is the legendary ancient city in Asia Minor that was the focal point of the Trojan War in Greek and Roman mythology.
  • E. Troy
    Troy is a suburban city in Michigan known for its strong business community, shopping centers, and role as a key part of the Detroit metropolitan area.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Troy
Triple: [Troy Perkins, givenName, Troy]
Generated description
Troy is an ancient city in northwestern Anatolia, famed as the setting of the Trojan War in Greek mythology and Homer’s epic poems.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Troy
Target entity description: Troy is an ancient city in northwestern Anatolia, famed as the setting of the Trojan War in Greek mythology and Homer’s epic poems.
  • A. 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.
  • B. Troy
    Troy is a 2004 epic historical war film loosely based on Homer's Iliad, depicting the legendary conflict between the Greeks and Trojans.
  • C. 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.
  • D. Troy
    Troy is a small city in southeastern Alabama known for being the home of Troy University and its vibrant college-town atmosphere.
  • E. Troy
    Troy is a suburban city in Michigan known for its strong business community, shopping centers, and role as a key part of the Detroit metropolitan area.
  • F. None of above.

Provenance (5 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_69ca82abaffc8190ab8af79cdbc31ab3 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3d73bf048190ad8066a7e95c34b0 completed March 31, 2026, 3:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc56acfcf88190a0e694f60f2907d2 completed March 31, 2026, 11:20 p.m.
NEDg Description generation batch_69cc58a9e94081908980e2c60be38642 completed March 31, 2026, 11:28 p.m.
NED2 Entity disambiguation (via description) batch_69cc5cb791b48190bd5004b518d23f84 completed March 31, 2026, 11:45 p.m.
Created at: March 30, 2026, 5:19 p.m.