Triple
T8521651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scarlet Knights |
E201705
|
entity |
| Predicate | mascot |
P52
|
FINISHED |
| Object | Scarlet Knight |
E38981
|
NE FINISHED |
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: Scarlet Knight | Statement: [Scarlet Knights, mascot, Scarlet Knight]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scarlet Knight Context triple: [Scarlet Knights, mascot, Scarlet Knight]
-
A.
Scarlet Knight
chosen
Scarlet Knight is the armored medieval knight mascot representing Rutgers University's athletic teams.
-
B.
Scarlet Lady
Scarlet Lady is a cruise ship operated by Virgin Voyages, known for its adults-only voyages and modern, boutique-style onboard experience.
-
C.
Scarlet
Scarlet is a studio album by American rapper and singer Doja Cat that showcases her shift toward a darker, more rap-focused sound.
-
D.
Scarlet
Scarlet is the alias of Will Scathelock, a character often associated with the Robin Hood legends.
-
E.
Flame Princess
Flame Princess is a fiery elemental royal from the animated series "Adventure Time," known for her volatile temper, flame-based powers, and complex relationship with Finn the Human.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca8321bb44819081b74df0b710276d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe62a490481908ee0ad4ba9a94682 |
completed | March 31, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce4e8399f481909992aedf0d918cbc |
completed | April 2, 2026, 11:09 a.m. |
Created at: March 30, 2026, 6:16 p.m.