Triple
T37512615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Worldstone |
E932552
|
entity |
| Predicate | corruptionEffect |
P54764
|
FINISHED |
| Object | threatened to twist all of Sanctuary |
—
|
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: threatened to twist all of Sanctuary | Statement: [Worldstone, corruptionEffect, threatened to twist all of Sanctuary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: corruptionEffect Context triple: [Worldstone, corruptionEffect, threatened to twist all of Sanctuary]
-
A.
corruptionLevel
Indicates the degree or extent to which unethical, illegal, or dishonest practices are present or influential in a given context.
-
B.
hasCorruptOfficials
Indicates that an entity possesses or is associated with officials who engage in corrupt or unethical behavior.
-
C.
corrupts
chosen
Indicates that one entity causes another entity, system, or process to become morally, functionally, or structurally degraded or impaired.
-
D.
stanceOnCorruption
Indicates a subject’s expressed position, attitude, or policy regarding corruption.
-
E.
courtCorruption
Indicates that a court or judicial body is involved in corrupt practices, such as bribery, bias, or abuse of legal authority.
- 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba5eec0448190a5e6f0c43fdcd0e3 |
completed | May 6, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69fba34edd548190bfa980e6e16e0a88 |
completed | May 6, 2026, 8:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.