Triple
T19134889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | frozen lake of Cocytus |
E468409
|
entity |
| Predicate | inhabitantCondition |
P132337
|
FINISHED |
| Object | sinners trapped in ice |
—
|
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: sinners trapped in ice | Statement: [frozen lake of Cocytus, inhabitantCondition, sinners trapped in ice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inhabitantCondition Context triple: [frozen lake of Cocytus, inhabitantCondition, sinners trapped in ice]
-
A.
inhabitedBy
Indicates that a place or location is lived in or occupied by a particular individual, group, or species.
-
B.
hasInhabitantsCharacteristic
chosen
Indicates that a place or region is associated with a particular characteristic, quality, or attribute of its inhabitants.
-
C.
stateInhabited
Indicates that a particular state is (or was) lived in or occupied by a specified entity.
-
D.
inhabitantOf
Indicates that an entity lives in or resides within a specified place or location.
-
E.
inhabitedIn
Indicates that an entity lives, resides, or has its dwelling within a specified place or location.
- 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_69d8dd0796a48190b34ce4cd9d3f3be5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e3ec4c848190af450bf5bf8db5e7 |
completed | April 20, 2026, 8:29 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b475d88190a8c15e8eb01dbfef |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:05 p.m.