Triple
T36267111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Town of St. Marys |
E892255
|
entity |
| Predicate | hasHeritageBuildingMaterial |
P112113
|
FINISHED |
| Object | limestone |
—
|
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: limestone | Statement: [Town of St. Marys, hasHeritageBuildingMaterial, limestone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHeritageBuildingMaterial Context triple: [Town of St. Marys, hasHeritageBuildingMaterial, limestone]
-
A.
hasArchitecturalMaterial
chosen
Indicates that something is constructed from, incorporates, or is characterized by a particular architectural material.
-
B.
hasHeritageElements
Indicates that something contains or includes elements that are part of a cultural, historical, or natural heritage.
-
C.
hasStationBuildingMaterial
Indicates that a station’s building is constructed from, or primarily composed of, a specified material.
-
D.
hasHeritageUse
Indicates that something is used, managed, or valued in a way that relates to cultural, historical, or natural heritage.
-
E.
hasBuildingMaterialInHut
Indicates that a hut is constructed using a specified building material.
- 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_69f76e4699188190af045b11a840ce31 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fdb45537288190b6791078d4a6899f |
completed | May 8, 2026, 10 a.m. |
| PD | Predicate disambiguation | batch_69fdb39ad96481908376d7def9fafc13 |
completed | May 8, 2026, 9:57 a.m. |
Created at: May 3, 2026, 4:09 p.m.