Triple
T26164956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Dix |
E654223
|
entity |
| Predicate | USGSQuadrangle |
P88429
|
FINISHED |
| Object | Elizabethtown |
—
|
NE NERFINISHED |
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: Elizabethtown | Statement: [South Dix, USGSQuadrangle, Elizabethtown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: USGSQuadrangle Context triple: [South Dix, USGSQuadrangle, Elizabethtown]
-
A.
hasSummitUSGSQuadrangle
chosen
Indicates that the summit of a geographic feature is located within a specific USGS topographic quadrangle map.
-
B.
topographicMap
Indicates a mapping relationship where a representation shows the physical terrain features and elevation contours of a geographic area.
-
C.
topographicMapMaker
Indicates that one entity creates or produces topographic maps representing the physical features and elevations of a geographic area for another entity or context.
-
D.
topographicMapSeries
Indicates that one entity is a topographic map belonging to a specific series or set of related topographic maps associated with another entity.
-
E.
cartographicSource
Indicates the map, chart, or other cartographic resource from which the described information or representation is derived.
- 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_69ee5b44391c81908bdbd8813ba9aa99 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60c3e162c819086e1111cdba01ab6 |
completed | May 2, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:32 p.m.