Triple
T28612197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Klondike |
E724191
|
entity |
| Predicate | typicalWinCondition |
P20842
|
FINISHED |
| Object | all cards moved to foundations |
—
|
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: all cards moved to foundations | Statement: [Klondike, typicalWinCondition, all cards moved to foundations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalWinCondition Context triple: [Klondike, typicalWinCondition, all cards moved to foundations]
-
A.
conditionOfVictory
chosen
Indicates the specific circumstances or criteria under which a participant is considered to have won.
-
B.
classWins
Indicates that a particular class has achieved victory or success in a competitive context.
-
C.
hasWinningCondition
Indicates that a particular condition or set of conditions determines when a participant, entity, or process is considered to have won or successfully completed a defined objective.
-
D.
winnerWins
Indicates that the entity identified as the winner achieves victory over another entity or in a specified competition or event.
-
E.
typeOfVictory
Indicates the specific manner or category in which a victory was achieved.
- 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_69f01d816d7c8190a1fe27e3434041dc |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_6a00cbae75988190974f5b45a2e62326 |
completed | May 10, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_6a00cabe4c5881909cca5efbe494e0d1 |
completed | May 10, 2026, 6:13 p.m. |
Created at: April 28, 2026, 4:30 a.m.