Triple
T15189471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Switch Island |
E362965
|
entity |
| Predicate | upgradeImplemented |
P23568
|
FINISHED |
| Object | signalisation improvements |
—
|
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: signalisation improvements | Statement: [Switch Island, upgradeImplemented, signalisation improvements]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upgradeImplemented Context triple: [Switch Island, upgradeImplemented, signalisation improvements]
-
A.
upgradeMethod
Indicates the method or process by which something is improved, updated, or elevated to a higher level or version.
-
B.
upgradeType
chosen
Indicates the specific kind or category of improvement or enhancement applied to an entity relative to its previous state.
-
C.
upgradePath
Indicates the relationship by which one entity can be improved, enhanced, or transitioned into another, typically more advanced, version or state.
-
D.
upgradeGoal
Indicates that an entity has a target or intended improvement to a higher level, version, or state relative to its current condition.
-
E.
upgradeProgram
Indicates that one entity improves, enhances, or replaces another entity’s program with a more advanced or updated version.
- 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_69d85a09a39c81908759f23268e2d408 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0067beedc8190abc0a94c7a38f85e |
completed | April 15, 2026, 9:43 p.m. |
| PD | Predicate disambiguation | batch_69deb97bd8bc8190b2ad4888f97cf963 |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:10 a.m.