Triple
T5507603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lewisham, London, England |
E144478
|
entity |
| Predicate | locatedInDirectionFromCharingCross |
P16893
|
FINISHED |
| Object | southeast |
—
|
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: southeast | Statement: [Lewisham, London, England, locatedInDirectionFromCharingCross, southeast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInDirectionFromCharingCross Context triple: [Lewisham, London, England, locatedInDirectionFromCharingCross, southeast]
-
A.
directionFromCharingCross
chosen
Indicates the compass direction of one place or object as measured from Charing Cross.
-
B.
distanceToCharingCross
Indicates the spatial distance between a given location and Charing Cross.
-
C.
directionFromCityCentre
Indicates the compass direction in which one location lies relative to the city centre.
-
D.
directionFromCityCenter
Indicates the compass direction in which one location lies relative to the city center.
-
E.
nearJunctionOf
Indicates that one entity is located close to the point where two or more linear features (such as roads, tracks, or paths) meet or intersect.
- 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_69c008f6b5048190a09064116062cf69 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f495c588190b0cfe5bfb3d2c221 |
completed | March 22, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69c01b07bde08190b3933b96bdc70dd5 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:32 p.m.