Triple
T4795369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maerdy |
E106697
|
entity |
| Predicate | positionInValley |
P56914
|
FINISHED |
| Object | head of the Rhondda Fach valley |
—
|
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: head of the Rhondda Fach valley | Statement: [Maerdy, positionInValley, head of the Rhondda Fach valley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInValley Context triple: [Maerdy, positionInValley, head of the Rhondda Fach valley]
-
A.
isInValley
chosen
Indicates that an entity is located within or occupies the area of a valley.
-
B.
hasValley
Indicates that one entity contains, features, or is characterized by the presence of a valley associated with the other entity.
-
C.
adjacentValley
Indicates that one valley is directly next to or bordering another valley.
-
D.
liesBetweenValleys
Indicates that something is positioned in the area or region separating two valleys.
-
E.
lowestPoint
Indicates that one entity is the point with the minimum vertical position or value relative to another entity or within a specified context.
- 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_69bd43f591c881909e5a532388b0f3f3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6b40c29c8190adab3503f8ba0145 |
completed | March 20, 2026, 3:44 p.m. |
| PD | Predicate disambiguation | batch_69bd622f88188190a51d52ccfad3d2dd |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:22 p.m.