Triple
T38188790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London–Manchester |
E1005393
|
entity |
| Predicate | hasDirectionFromLondon |
P15847
|
FINISHED |
| Object | north-west |
—
|
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: north-west | Statement: [London–Manchester, hasDirectionFromLondon, north-west]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectionFromLondon Context triple: [London–Manchester, hasDirectionFromLondon, north-west]
-
A.
directionFromLondon
chosen
Indicates the cardinal or relative compass direction of an entity’s location when measured from London.
-
B.
isInDirectionTowardsCentralLondon
Indicates that something is oriented or moving in the direction leading toward central London.
-
C.
lineDirectionFromCentralLondon
Indicates the directional bearing or route of a line as measured outward from a central reference point in London.
-
D.
directionFromLondonPaddington
Indicates the compass direction or bearing of a place or object when measured starting from London Paddington station.
-
E.
directionFromLondonEuston
Indicates the compass direction or bearing of an entity when measured starting from London Euston as the reference point.
- 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_69f76dbc22c481908139b694ffde7a0c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ffb69812808190a751853b30183e65 |
completed | May 9, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69ffb63bdda88190a9dd8426dc0bad43 |
completed | May 9, 2026, 10:33 p.m. |
Created at: May 3, 2026, 4:29 p.m.