Triple
T6912553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Jose Sharks |
E159971
|
entity |
| Predicate | mascot |
P52
|
FINISHED |
| Object | SJ Sharkie |
E159970
|
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: SJ Sharkie | Statement: [San Jose Sharks, mascot, SJ Sharkie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SJ Sharkie Context triple: [San Jose Sharks, mascot, SJ Sharkie]
-
A.
SJ Sharkie
chosen
SJ Sharkie is the playful, anthropomorphic shark who serves as the official mascot and fan ambassador for the NHL’s San Jose Sharks.
-
B.
Sharkie
Sharkie is the official mascot of the Sharks rugby union team, typically depicted as a friendly anthropomorphic shark that entertains fans at matches and events.
-
C.
Rikki Jai
Rikki Jai is a prominent Trinidadian singer known for helping popularize chutney and chutney-soca music in the Caribbean.
-
D.
Shazzer
Shazzer is one of Bridget Jones’s outspoken, feminist best friends in the romantic comedy film "Bridget Jones: The Edge of Reason."
-
E.
Rockey
Rockey is the surname of Keller E. Rockey, a notable United States Marine Corps general who served during World War II.
- 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_69c68839ccb88190b4aa5cc1aca3448f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d9c2e79881909eeb061be0a72bdf |
completed | March 27, 2026, 7:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7490c95548190a493d3fd23d1d7a5 |
completed | March 28, 2026, 3:20 a.m. |
Created at: March 27, 2026, 2:25 p.m.