Triple
T683933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glasgow Subway |
E13240
|
entity |
| Predicate | modernisation |
P4337
|
FINISHED |
| Object | major refurbishment in late 1970s |
—
|
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: major refurbishment in late 1970s | Statement: [Glasgow Subway, modernisation, major refurbishment in late 1970s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: modernisation Context triple: [Glasgow Subway, modernisation, major refurbishment in late 1970s]
-
A.
modernization
chosen
Indicates a process by which something is updated, reformed, or transformed to align with contemporary standards, technologies, or practices.
-
B.
modernizationFeatures
Indicates that something includes characteristics, elements, or improvements associated with making it more modern or up to date.
-
C.
modernUse
Indicates how something is currently used or applied in modern times.
-
D.
modernizedBy
Indicates that an entity has been updated, improved, or brought up to modern standards through the actions or influence of another entity.
-
E.
modernPractice
Indicates that an entity engages in or reflects a contemporary, up-to-date way of doing something, following current methods, standards, or trends.
- 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_69a4933e0f98819097d22766c49b61b8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a0725c708190aa6edfee742ca4e6 |
completed | March 1, 2026, 8:24 p.m. |
| PD | Predicate disambiguation | batch_69a49d1f0ccc819088c1527beabcb718 |
completed | March 1, 2026, 8:10 p.m. |
Created at: March 1, 2026, 7:36 p.m.