Triple
T25543265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epping to Ongar branch |
E640226
|
entity |
| Predicate | lineColourOnMap |
P62095
|
FINISHED |
| Object | red (Central line colour) |
—
|
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: red (Central line colour) | Statement: [Epping to Ongar branch, lineColourOnMap, red (Central line colour)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lineColourOnMap Context triple: [Epping to Ongar branch, lineColourOnMap, red (Central line colour)]
-
A.
mapColorLine
Indicates a relationship where a specific color is assigned to or associated with a particular line (such as a route, path, or boundary) on a map.
-
B.
mapColorLines
Indicates a relationship where colors are assigned or associated with specific lines, such as mapping each line to a particular color.
-
C.
mapColorGreenLine
Indicates that an entity is represented or highlighted with a green-colored line on a map.
-
D.
mapColor_RedLine
chosen
Indicates that a map element is represented or highlighted using a red line.
-
E.
mapColorBlueLine
Indicates that a map is rendered or highlighted using a blue-colored line to represent a particular feature or path.
- 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_69e75dbfff7081909b0aa779d48321d2 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f895e458819081cf031b70d20e56 |
completed | May 2, 2026, 1:13 p.m. |
| PD | Predicate disambiguation | batch_69f480789be08190ab252a6de3797200 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 3:27 p.m.