Triple
T30292992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Slow Mutants |
E770430
|
entity |
| Predicate | menaces |
P956
|
FINISHED |
| Object | the protagonist in an underground passage |
—
|
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: the protagonist in an underground passage | Statement: [The Slow Mutants, menaces, the protagonist in an underground passage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: menaces Context triple: [The Slow Mutants, menaces, the protagonist in an underground passage]
-
A.
threatsFaced
Indicates that an entity is exposed to or experiences specific dangers, risks, or harmful conditions.
-
B.
threatenedBy
chosen
Indicates that one entity poses a danger or potential harm to another entity.
-
C.
threatToHumans
Indicates that the subject poses or represents a potential danger, harm, or risk to humans.
-
D.
threatensToDestroy
Indicates that one entity has expressed an intention or warning that it will cause the complete ruin or elimination of another entity or object.
-
E.
threat
Indicates a relationship where one entity expresses or poses potential harm, danger, or negative consequences toward another entity.
- 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_69f224875c288190a9b96b975006ec4a |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6813474208190b3e2f0ad7d2b9aab |
completed | May 2, 2026, 10:56 p.m. |
| PD | Predicate disambiguation | batch_69f6760216108190bbb708d53a6c2c25 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:47 p.m.