Triple
T5911038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | kibisis |
E131457
|
entity |
| Predicate | dangerContained |
P16293
|
FINISHED |
| Object | petrifying power of Medusa’s gaze |
—
|
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: petrifying power of Medusa’s gaze | Statement: [kibisis, dangerContained, petrifying power of Medusa’s gaze]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dangerContained Context triple: [kibisis, dangerContained, petrifying power of Medusa’s gaze]
-
A.
dangerWarning
Indicates that one entity issues or represents a warning about potential danger associated with another entity or situation.
-
B.
inDangerSince
Indicates that an entity has been in a state of danger continuously starting from a specified point in time.
-
C.
hasNotableHazard
chosen
Indicates that an entity is associated with a significant risk, danger, or harmful condition that is noteworthy or exceptional.
-
D.
endangerment
Indicates a relationship in which one entity exposes another to potential harm, risk, or danger.
-
E.
underDangerList
Indicates that an entity is classified as being on a designated danger or endangered list, signifying it is at risk or under threat.
- 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_69c008593a44819081a07ae0efe6c574 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c048fc112c8190b905bf561c9de096 |
completed | March 22, 2026, 7:54 p.m. |
| PD | Predicate disambiguation | batch_69c03352208c8190968efed05a9fd416 |
completed | March 22, 2026, 6:22 p.m. |
Created at: March 22, 2026, 3:59 p.m.