Triple
T28811233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruins of the Greek Theatre at Taormina |
E727516
|
entity |
| Predicate | depictsTypeOfPlace |
P125859
|
FINISHED |
| Object | ancient ruin |
—
|
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: ancient ruin | Statement: [Ruins of the Greek Theatre at Taormina, depictsTypeOfPlace, ancient ruin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsTypeOfPlace Context triple: [Ruins of the Greek Theatre at Taormina, depictsTypeOfPlace, ancient ruin]
-
A.
depictsBuildingType
chosen
Indicates that one entity visually represents or portrays a specific type or category of building associated with another entity.
-
B.
portraysPlace
Indicates that one entity visually or narratively represents or depicts a particular place.
-
C.
placeOfDepiction
Indicates the location or setting where the depicted subject is shown as being situated in the representation.
-
D.
depictsFictionalPlace
Indicates that one entity visually represents or portrays a place that exists only in fiction rather than in the real world.
-
E.
placeType
Indicates the type or category of place associated with an entity (e.g., city, park, building).
- 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_69f0319c38948190bca746ad60fd25ba |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 28, 2026, 6:31 a.m.