Triple

T8834536
Position Surface form Disambiguated ID Type / Status
Subject Sinéad O’Connor E210232 entity
Predicate composerOf P1142 FINISHED
Object Troy
"Troy" is a powerful early single by Irish singer-songwriter Sinéad O’Connor, known for its intense emotional delivery and poetic lyrics.
 E760083 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: [Sinéad O’Connor, composerOf, Troy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Troy
Context triple: [Sinéad O’Connor, composerOf, 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: [Sinéad O’Connor, composerOf, Troy]
Generated description
"Troy" is a powerful early single by Irish singer-songwriter Sinéad O’Connor, known for its intense emotional delivery and poetic lyrics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Troy
Target entity description: "Troy" is a powerful early single by Irish singer-songwriter Sinéad O’Connor, known for its intense emotional delivery and poetic lyrics.
  • 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 masculine given name of ancient origin, famously borne by former NFL quarterback Troy Aikman.
  • C. Troy
    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 small city in southeastern Alabama known for being the home of Troy University and its vibrant college-town atmosphere.
  • E. 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.
  • F. None of above. chosen

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_69ca8388549c819095fd94eadefbb007 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60686cac8190b3138db40b6fe058 completed April 1, 2026, 12:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69cf8975a6f481908ee435d0435c8ffb completed April 3, 2026, 9:33 a.m.
NEDg Description generation batch_69cf8a8e5db0819080e6fdc3d8322e94 completed April 3, 2026, 9:38 a.m.
NED2 Entity disambiguation (via description) batch_69cf8b8849ec8190915fa087b1b46c18 completed April 3, 2026, 9:42 a.m.
Created at: March 30, 2026, 6:47 p.m.