Triple
T22247502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troy Trojans |
E549882
|
entity |
| Predicate | hasMascot |
P52
|
FINISHED |
| Object | T-Roy |
—
|
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: T-Roy | Statement: [Troy Trojans, hasMascot, T-Roy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: T-Roy Context triple: [Troy Trojans, hasMascot, T-Roy]
-
A.
T-Roy
chosen
T-Roy is the costumed Trojan warrior mascot who represents Troy University at athletic events and campus activities.
-
B.
Trouble T Roy
Trouble T Roy was an American hip hop dancer and performer best known as a member of Heavy D & the Boyz whose tragic accidental death inspired several notable tribute songs in the early 1990s.
-
C.
T-Ray
T-Ray is a powerful sorcerer and mercenary in Marvel Comics who serves as one of Deadpool’s most dangerous and obsessive arch-enemies.
-
D.
T-Ray
T-Ray is a hip-hop record producer known for his gritty, sample-heavy beats and work with prominent rap artists in the 1990s.
-
E.
Troy Noka
Troy Noka is a music producer known for his work in contemporary R&B and pop, collaborating with prominent artists such as Doja Cat.
- 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_69e11e41d9408190bd770cf282e22753 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f13219dc3481908dd987c4e98623e6 |
completed | April 28, 2026, 10:18 p.m. |
Created at: April 16, 2026, 8:38 p.m.