Triple
T4736918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phaeacians |
E105146
|
entity |
| Predicate | punishmentMotif |
P2287
|
FINISHED |
| Object | ship turned to stone by Poseidon in some versions |
—
|
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: ship turned to stone by Poseidon in some versions | Statement: [Phaeacians, punishmentMotif, ship turned to stone by Poseidon in some versions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: punishmentMotif Context triple: [Phaeacians, punishmentMotif, ship turned to stone by Poseidon in some versions]
-
A.
aimOfPunishment
Indicates that a specified purpose or objective is the intended goal or rationale behind a particular act of punishment.
-
B.
punishedBy
chosen
Indicates that an entity receives punishment administered by another entity.
-
C.
punishmentLocation
Indicates the place or setting where a punishment is carried out or imposed.
-
D.
hasPunishment
Indicates that an entity is subject to a specified penalty, sanction, or adverse consequence as a result of some action, condition, or rule.
-
E.
punishedGenerationOf
Indicates that one entity imposed a punitive consequence on another entity or group, typically as a result of the latter’s actions or behavior.
- 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_69bd43ee52048190b81a4f066534ffb3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64831c58819098758ac1f7839b3a |
completed | March 20, 2026, 3:15 p.m. |
| PD | Predicate disambiguation | batch_69bd6221c3b881908604f35f8de6f16b |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:19 p.m.