Triple
T34701652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parks Road, Oxford |
E1000385
|
entity |
| Predicate | hasLandmarkAtSouthernEnd |
P5249
|
FINISHED |
| Object | Clarendon Building, Oxford |
E56450
|
NE 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: Clarendon Building, Oxford | Statement: [Parks Road, Oxford, hasLandmarkAtSouthernEnd, Clarendon Building, Oxford]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLandmarkAtSouthernEnd Context triple: [Parks Road, Oxford, hasLandmarkAtSouthernEnd, Clarendon Building, Oxford]
-
A.
locatedAtSouthernFootOf
Indicates that one entity is situated at the southern base or lower slope of another entity, typically a hill, mountain, or similar landform.
-
B.
hasSouthernTerminus
chosen
Indicates that one entity serves as the southern endpoint or terminus of another entity, such as a route, line, or path.
-
C.
isOneOfSouthernmostPointsOf
Indicates that something is among the furthest-south locations within a specified area or set.
-
D.
isSouthernmostPartOf
Indicates that one entity is the geographically furthest south portion or section of another entity.
-
E.
isOnNorthernTipOf
Indicates that one entity is located at or forms the northernmost extremity or tip of another entity.
- F. None of above.
Provenance (4 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_69f76dab937881909c86f1b9ad50445f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69ff4fc6077c8190b8fd9b43fcfde986 |
completed | May 9, 2026, 3:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37530598488190b7de90e35623cb37 |
completed | June 21, 2026, 2:57 a.m. |
| PD | Predicate disambiguation | batch_69ff4e61fb648190a72f7918961ece9c |
completed | May 9, 2026, 3:10 p.m. |
Created at: May 3, 2026, 3:59 p.m.