Triple
T15915588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | STK Orlando |
E385960
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | STK |
E965469
|
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: STK | Statement: [STK Orlando, brand, STK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: STK Context triple: [STK Orlando, brand, STK]
-
A.
STK
STK is the National Rail station code for South Kensington railway station in London, United Kingdom.
-
B.
STK
STK is the standard abbreviation used for the Stockton Heat, a former professional ice hockey team that played in the American Hockey League as the Calgary Flames’ affiliate.
-
C.
STK
STK is the common abbreviation used for the St Kilda Football Club, an Australian rules football team in the Australian Football League (AFL).
-
D.
STK
chosen
STK is a trendy, high-energy modern steakhouse and lounge known for its stylish atmosphere, DJ-driven music, and upscale dining experience.
-
E.
S Stock
S Stock is a class of electric multiple unit trains used on the London Underground’s sub-surface lines.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1566216d481908dd6e3acaa26fd45 |
completed | April 16, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb05b15e8819083b67afa52f46283 |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.