Triple
T156579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prometheus |
E3193
|
entity |
| Predicate | action |
P6944
|
FINISHED |
| Object | stole fire back for humans |
—
|
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: stole fire back for humans | Statement: [Prometheus, action, stole fire back for humans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: action Context triple: [Prometheus, action, stole fire back for humans]
-
A.
activity
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
-
B.
attackType
Indicates the specific method, style, or category of attack used in an aggressive or hostile action between entities.
-
C.
independenceDay
Indicates the date or event on which an entity (typically a country or region) formally celebrates its independence from another governing authority.
-
D.
faction
Indicates that an entity is formally affiliated with, or belongs to, a particular faction or organized group within a broader context.
-
E.
traction
Indicates the degree to which one entity’s movement or influence effectively grips, pulls, or gains momentum relative to another entity or medium.
- F. None of above. chosen
Provenance (4 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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a258808ff08190a06b6206f635612b |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a2565ded588190a27319aaa0130b4f |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a2587f1fe48190b1235aa63448fec5 |
completed | Feb. 28, 2026, 2:52 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.