Triple
T37103714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dongsi South Street |
E918778
|
entity |
| Predicate | hasDirectionEnd |
P200291
|
FINISHED |
| Object | south |
—
|
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: south | Statement: [Dongsi South Street, hasDirectionEnd, south]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectionEnd Context triple: [Dongsi South Street, hasDirectionEnd, south]
-
A.
hasDirectionEndpoints
Indicates that a directional element is defined or bounded by specific start and end points.
-
B.
hasDirectionStart
chosen
Indicates that a directional element or path begins or originates from a specified starting point.
-
C.
hasDirectionType
Indicates that something possesses or is associated with a specific type or category of direction.
-
D.
containsDirectionOf
Indicates that one entity includes or encompasses the directional orientation or path associated with another entity.
-
E.
hasDirectionReference
Indicates that one entity specifies or points to a directional orientation or reference frame for another entity.
- 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_69f76e9b99c8819096164b21ff5bd996 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff7fc835f08190afd1f8129b7a62a2 |
completed | May 9, 2026, 6:41 p.m. |
| PD | Predicate disambiguation | batch_69ff7f2e99ac8190ba372a1358a05a30 |
completed | May 9, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:14 p.m.