Triple

T18318505
Position Surface form Disambiguated ID Type / Status
Subject Street Cry E438808 entity
Predicate damsire P56417 FINISHED
Object Troy
Troy was a top-class British Thoroughbred racehorse best known for winning the 1979 Epsom Derby in record time and being regarded as one of the outstanding middle-distance horses of his era.
 E1307188 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: [Street Cry, damsire, Troy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Troy
Context triple: [Street Cry, damsire, 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
    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. 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: [Street Cry, damsire, Troy]
Generated description
Troy was a top-class British Thoroughbred racehorse best known for winning the 1979 Epsom Derby in record time and being regarded as one of the outstanding middle-distance horses of his era.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Troy
Target entity description: Troy was a top-class British Thoroughbred racehorse best known for winning the 1979 Epsom Derby in record time and being regarded as one of the outstanding middle-distance horses of his era.
  • A. Troy chosen
    Troy was a top-class British Thoroughbred racehorse best known for his dominant 1979 Epsom Derby victory and status as one of the outstanding middle-distance performers of his era.
  • 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 2004 epic historical war film loosely based on Homer's Iliad, depicting the legendary conflict between the Greeks and Trojans.
  • 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.

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_69d8b916a2d081909e249e4902f6aad9 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50aa342a881909afcd995405027af completed April 19, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03c4c6094881909add4e2fe99a1bba completed May 13, 2026, 12:24 a.m.
NEDg Description generation batch_6a03c52d0ba48190845d461df02c3aa3 completed May 13, 2026, 12:26 a.m.
NED2 Entity disambiguation (via description) batch_6a03c5dd07488190ae04c6b406ab29c9 completed May 13, 2026, 12:29 a.m.
Created at: April 10, 2026, 10:36 a.m.