Triple
T28667912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unaussprechlichen Kulten |
E725630
|
entity |
| Predicate | settingElementOf |
P135023
|
FINISHED |
| Object | Call of Cthulhu role-playing game |
—
|
NE NERFINISHED |
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: Call of Cthulhu role-playing game | Statement: [Unaussprechlichen Kulten, settingElementOf, Call of Cthulhu role-playing game]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: settingElementOf Context triple: [Unaussprechlichen Kulten, settingElementOf, Call of Cthulhu role-playing game]
-
A.
setElement
chosen
Indicates that a particular element is included as a member of a specified set.
-
B.
settingControlled
Indicates that one entity regulates, adjusts, or determines the configuration or parameters of another entity.
-
C.
setting
Indicates the place, time, or context in which an event, action, or interaction occurs.
-
D.
settingEvoked
Indicates that a particular setting or environment brings about, suggests, or calls to mind a specific response, mood, or association.
-
E.
settingAfter
Indicates that one setting or configuration occurs or is applied after another in a sequence or order.
- 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_69f01d85be388190b669a0e401e2f2c4 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6c49627908190b3553474c7c3072b |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f23ae081909a52801266063a3c |
completed | May 3, 2026, 3:41 a.m. |
Created at: April 28, 2026, 5:02 a.m.