Triple
T20686266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Detroit Mercy Titans |
E508425
|
entity |
| Predicate | mascot |
P52
|
FINISHED |
| Object | Tommy Titan |
—
|
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: Tommy Titan | Statement: [Detroit Mercy Titans, mascot, Tommy Titan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tommy Titan Context triple: [Detroit Mercy Titans, mascot, Tommy Titan]
-
A.
Tommy Titan
chosen
Tommy Titan is the costumed athletic mascot representing the University of Detroit Mercy Titans at sporting events and school activities.
-
B.
Tommy Tar
Tommy Tar is the official mascot character representing the Tars athletic teams.
-
C.
Tommy Vega
Tommy Vega is a fictional paramedic captain and devoted mother featured in the television drama series "9-1-1: Lone Star."
-
D.
Tommy
Tommy is a masculine given name, often a diminutive of Thomas, used in various English-speaking countries.
-
E.
Tommy
Tommy is one of the alternate personalities (alters) of the soap opera character Victoria "Viki" Lord from the series One Life to Live.
- 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6beacc30081908e57cd7f2c3ef047 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 11:45 a.m.