Triple
T20730473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Zeus at Olympia |
E509558
|
entity |
| Predicate | hasColumnDrums |
P141281
|
FINISHED |
| Object | re-erected column on site |
—
|
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: re-erected column on site | Statement: [Temple of Zeus at Olympia, hasColumnDrums, re-erected column on site]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasColumnDrums Context triple: [Temple of Zeus at Olympia, hasColumnDrums, re-erected column on site]
-
A.
usesDrums
Indicates that an entity employs drums as instruments or tools in performing an action or carrying out an activity.
-
B.
hasDrummer
Indicates that one entity serves as the drummer for, or plays drums in, another entity such as a band or musical group.
-
C.
hasDrumProgrammingBy
Indicates that the drum programming for a work (such as a song or track) is created or performed by a specified entity.
-
D.
hasDrumSolo
Indicates that a musical performance, track, or section contains a featured solo passage played on drums.
-
E.
hasRhythmSection
Indicates that an entity (such as a musical group or piece) includes or is associated with a rhythm section component.
- 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_69e0b4c589c08190834fb5d86d0efa2b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1ec9820819093a07f90503686b2 |
completed | April 21, 2026, 12:16 a.m. |
| PD | Predicate disambiguation | batch_69e5c04b31248190b9b9d91b5cb854e3 |
completed | April 20, 2026, 5:57 a.m. |
| PDg | Predicate description generation | batch_69e5c3cbe5788190b7ace43bfdac2ef6 |
completed | April 20, 2026, 6:12 a.m. |
Created at: April 16, 2026, 12:30 p.m.