Triple
T38587260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stockade Prison |
E932372
|
entity |
| Predicate | originalRecommendedLevelRange |
P187802
|
FINISHED |
| Object | around level 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: around level 20–30 | Statement: [Stockade Prison, originalRecommendedLevelRange, around level 20–30]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalRecommendedLevelRange Context triple: [Stockade Prison, originalRecommendedLevelRange, around level 20–30]
-
A.
recommendedLevelRangeRetail
Indicates the range of levels at which a product is recommended to be sold or used in a retail context.
-
B.
startingLevelRange
Indicates the range of initial levels at which an entity, activity, or state begins.
-
C.
intendedPlayerLevel
Indicates the player level for which something (such as content, an item, or a challenge) is designed or meant to be used.
-
D.
recommendedLevelAtLaunch
chosen
Indicates the level that is advised or expected for an entity at the moment it is first introduced or made available.
-
E.
requiresLevelRange
Indicates that something is only applicable, accessible, or valid for entities whose level falls within a specified minimum-to-maximum range.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.