Triple
T508205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deep Ellum |
E10547
|
entity |
| Predicate | streetNameOrigin |
P3325
|
FINISHED |
| Object | corruption of "Deep Elm" |
—
|
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: corruption of "Deep Elm" | Statement: [Deep Ellum, streetNameOrigin, corruption of "Deep Elm"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: streetNameOrigin Context triple: [Deep Ellum, streetNameOrigin, corruption of "Deep Elm"]
-
A.
roadName
Indicates the specific name assigned to a road that identifies it within a transportation or address system.
-
B.
hasStreet
Indicates that an entity is located on, associated with, or identified by a particular street.
-
C.
streetNetwork
Indicates the layout and connectivity relationships among streets within a geographic area, including how roads intersect, link, and form a navigable network.
-
D.
streetSectionOf
Indicates that one street segment or portion belongs to, is contained within, or forms part of a larger street or roadway.
-
E.
hasNameOrigin
chosen
Indicates that the origin or source of an entity’s name is specified by the related entity.
- 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_69a2e848adf881908e5e04f7af030093 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f14dcd688190ad47a3b31b95b6d4 |
completed | Feb. 28, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69a2edfe236481909901cc7d4281b33c |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.