Triple
T36956387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ollie Starkey |
E914199
|
entity |
| Predicate | countryOfGameDeveloper |
P79843
|
FINISHED |
| Object | Canada |
E14901
|
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: Canada | Statement: [Ollie Starkey, countryOfGameDeveloper, Canada]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryOfGameDeveloper Context triple: [Ollie Starkey, countryOfGameDeveloper, Canada]
-
A.
countryOfDeveloper
chosen
Indicates the country in which the developer of an entity (such as a product, software, or work) is based or originates.
-
B.
countryOfGameOrigin
Indicates the country where a game was originally created, developed, or first produced.
-
C.
developerOfContainingGame
Indicates that an entity is the developer responsible for creating the game that contains the referenced element or component.
-
D.
gameDeveloperOfOrigin
Indicates that an entity is the original creator or primary developing studio responsible for a particular game.
-
E.
homeGamesCountry
Indicates the country in which an entity’s home games are played.
- F. None of above.
Provenance (4 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_69f76e8b28848190abd81fe7a7374910 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a0338d1074481909541e6150307e7f8 |
completed | May 12, 2026, 2:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3e2c3648d48190bab863d38dd6abf7 |
completed | June 26, 2026, 7:37 a.m. |
| PD | Predicate disambiguation | batch_6a03386e7da08190b533cb0e908503dd |
completed | May 12, 2026, 2:25 p.m. |
Created at: May 3, 2026, 4:13 p.m.