Triple
T11106997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lạc Long Quân Street |
E262656
|
entity |
| Predicate | orientationRelativeToWestLake |
P73279
|
FINISHED |
| Object | western edge |
—
|
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: western edge | Statement: [Lạc Long Quân Street, orientationRelativeToWestLake, western edge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orientationRelativeToWestLake Context triple: [Lạc Long Quân Street, orientationRelativeToWestLake, western edge]
-
A.
valleyOrientation
Indicates the directional alignment or bearing along which a valley extends across the landscape.
-
B.
directionRelativeToGyre
Indicates the orientation or heading of something in relation to the rotational flow or center of a gyre.
-
C.
cliffOrientation
Indicates the directional facing or alignment of a cliff relative to a reference frame (e.g., compass direction or slope aspect).
-
D.
directionRelativeTo
chosen
Indicates the spatial orientation of one entity in relation to another, such as which way it faces or points relative to a reference entity.
-
E.
directionFromSun
Indicates the orientation or bearing of an entity as measured outward from the Sun.
- 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_69d6aa9a40d88190a373e2c7e48285db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79a6546d4819092187e9c12a30ed5 |
completed | April 9, 2026, 12:24 p.m. |
| PD | Predicate disambiguation | batch_69d7441cf8188190b8095f622c923156 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.