Triple
T20192928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pokémon Trading Card Game |
E493016
|
entity |
| Predicate | typicalGameLengthMinutes |
P15428
|
FINISHED |
| Object | 20–30 |
—
|
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: 20–30 | Statement: [Pokémon Trading Card Game, typicalGameLengthMinutes, 20–30]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalGameLengthMinutes Context triple: [Pokémon Trading Card Game, typicalGameLengthMinutes, 20–30]
-
A.
gameLength
chosen
Indicates the duration or total length of a game, typically measured in time or turns.
-
B.
gameLengthRule
Indicates a rule that specifies how long a game is allowed or required to last.
-
C.
typicalNumberOfGamesRange
Indicates the usual minimum and maximum number of games typically played in the associated context or setting.
-
D.
typicalGame
Indicates a relationship where one entity is characterized as a standard, representative, or commonly occurring example of a game for the other entity or context.
-
E.
typicalNumberOfPlayers
Indicates the usual or standard number of players involved in participating in an activity or game.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66ad654648190a27521e6e8ea40c5 |
completed | April 20, 2026, 6:05 p.m. |
| PD | Predicate disambiguation | batch_69e55b11124c8190babacf2a0fe2d057 |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:37 p.m.