Triple

T21923697
Position Surface form Disambiguated ID Type / Status
Subject Trojan plain E541384 entity
Predicate surrounds P7850 FINISHED
Object Troy
Troy is an ancient city in northwestern Anatolia, famed as the setting of the Trojan War in Greek mythology and the focus of Homer’s epic poem the Iliad.
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: [Trojan plain, surrounds, Troy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Troy
Context triple: [Trojan plain, surrounds, Troy]
  • A. Troy
    Troy is a small town located in Greenwood County in the U.S. state of South Carolina.
  • 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 small city in southeastern Alabama known for being the home of Troy University and its vibrant college-town atmosphere.
  • D. 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.
  • 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. 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: [Trojan plain, surrounds, Troy]
Generated description
Troy is an ancient city in northwestern Anatolia, famed as the setting of the Trojan War in Greek mythology and the focus of Homer’s epic poem the Iliad.
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 the focus of Homer’s epic poem the Iliad.
  • 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_69e0c47d74488190a15119108794a307 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1233dc504819083ee27e253805189 completed April 28, 2026, 9:14 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a5a17e4dc81909dd40d3e3051ae01 completed May 18, 2026, 12:15 a.m.
NEDg Description generation batch_6a0a5b5a751c8190a6766e87599f0396 completed May 18, 2026, 12:20 a.m.
NED2 Entity disambiguation (via description) batch_6a0a5bbedc408190987f621d98d8224a completed May 18, 2026, 12:22 a.m.
Created at: April 16, 2026, 7:45 p.m.