Triple
T14111978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Artemision Bronze |
E339659
|
entity |
| Predicate | armPosition |
P52684
|
FINISHED |
| Object | right arm extended to throw |
—
|
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: right arm extended to throw | Statement: [Artemision Bronze, armPosition, right arm extended to throw]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armPosition Context triple: [Artemision Bronze, armPosition, right arm extended to throw]
-
A.
positionInArms
Indicates that one entity is being held or carried within the arms of another entity.
-
B.
handPosition
chosen
Indicates the spatial location or orientation of a hand relative to a reference point or object.
-
C.
armType
Indicates the specific kind or configuration of an arm associated with an entity.
-
D.
armsControl
Indicates a relationship where parties engage in limiting, regulating, or reducing weapons and military capabilities, often through agreements or treaties.
-
E.
laterArm
Indicates that one event, state, or action occurs at a later time than another within the same arm or branch of a process or study.
- 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_69d81c6a95b481909e39111e0c1f31ee |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de600e6a688190a1243a30ae9b7157 |
completed | April 14, 2026, 3:41 p.m. |
| PD | Predicate disambiguation | batch_69de05b2f7e481908a9a7d40153234c0 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:22 p.m.