Triple
T33536794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guinness World Record for most ported video game |
E858956
|
entity |
| Predicate | associatedGameGenre |
P53697
|
FINISHED |
| Object | puzzle video game |
—
|
LITERAL 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: puzzle video game | Statement: [Guinness World Record for most ported video game, associatedGameGenre, puzzle video game]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedGameGenre Context triple: [Guinness World Record for most ported video game, associatedGameGenre, puzzle video game]
-
A.
gameGenreContext
chosen
Indicates the genre or type of game associated with a given game entity or gaming context.
-
B.
gameGenreDeveloped
Indicates that a particular game genre has been created, defined, or developed by a specific entity (such as a person, team, or organization).
-
C.
websiteGenre
Indicates the thematic category or type of content that a website is primarily associated with.
-
D.
targetGenre
Indicates the genre that something is specifically aimed at, categorized under, or intended to belong to.
-
E.
relatedGame
Indicates that one game has a notable connection or association with another game, such as shared content, themes, or series.
- F. None of above.
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_69f34978caf4819083f90eba4944d8e8 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379f505c88190ac0879ab422c3054 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:39 a.m.