Triple
T24223611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marlow, Buckinghamshire, England |
E601527
|
entity |
| Predicate | hasLocalRiverReach |
P165
|
FINISHED |
| Object | Marlow Reach |
—
|
NE NERFINISHED |
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: Marlow Reach | Statement: [Marlow, Buckinghamshire, England, hasLocalRiverReach, Marlow Reach]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLocalRiverReach Context triple: [Marlow, Buckinghamshire, England, hasLocalRiverReach, Marlow Reach]
-
A.
hasLocalNameForRiver
Indicates that an entity specifies the locally used name for a particular river.
-
B.
hasRiver
chosen
Indicates that a location or area contains, is traversed by, or is directly associated with a river.
-
C.
hasRiverBelow
Indicates that one entity is located above another such that a river lies physically below it.
-
D.
hasNearbyRiverStructure
Indicates that a river-related structure (such as a dam, bridge, or levee) is located close to the referenced entity.
-
E.
hasSettlementOnRiver
Indicates that a settlement is located on or directly adjacent to a specific river.
- 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_69e29537ca548190b94a37ebe1977caf |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f287dd148081909f02e521ad6043b1 |
completed | April 29, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69f1c448abec8190b87cbf9ed419a309 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, midnight