Triple
T36956847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rad |
E914209
|
entity |
| Predicate | hasReplayValue |
P99850
|
FINISHED |
| Object | high replayability due to procedural generation |
—
|
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: high replayability due to procedural generation | Statement: [Rad, hasReplayValue, high replayability due to procedural generation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReplayValue Context triple: [Rad, hasReplayValue, high replayability due to procedural generation]
-
A.
hasReplay
Indicates that an event, action, or interaction is available to be viewed or experienced again in a recorded or reconstructed form.
-
B.
hasReplayStage
Indicates that an event, process, or competition includes a replay phase or stage in its structure.
-
C.
hasReplayWindow
Indicates that an entity has a defined time period during which a past event, action, or content can be replayed or re-accessed.
-
D.
isReplay
Indicates that an event, action, or content instance is a repeated playback or reproduction of a previously occurring original.
-
E.
hasReplayabilityFocus
chosen
Indicates that something is designed or evaluated with an emphasis on being enjoyable or worthwhile to experience multiple times.
- 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_69f76e8b28848190abd81fe7a7374910 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a10036481909c71188b2a0e7f04 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:13 p.m.