Triple
T29369230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shendu Highway depot |
E744807
|
entity |
| Predicate | locationRelativeToLine |
P38325
|
FINISHED |
| Object | southern end of Shanghai Metro Line 8 |
—
|
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: southern end of Shanghai Metro Line 8 | Statement: [Shendu Highway depot, locationRelativeToLine, southern end of Shanghai Metro Line 8]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationRelativeToLine Context triple: [Shendu Highway depot, locationRelativeToLine, southern end of Shanghai Metro Line 8]
-
A.
positionOnLine
chosen
Indicates that one entity occupies a specific location along a defined line or linear path in relation to another.
-
B.
locationRelativeToBorder
Indicates the position or placement of something in relation to a specified border or boundary.
-
C.
lineagePosition
Indicates the relative placement or rank of an entity within a lineage or ancestral chain.
-
D.
locationRelativeToPitch
Indicates the spatial position of an entity in relation to the pitch (e.g., above, beside, or within the pitch area).
-
E.
positionRelativeToSurface
Indicates how an entity is spatially located or oriented with respect to a reference surface.
- 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_69f0a79ba954819094597628112c6091 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_6a00233e2170819084bee0c8f74cc1a4 |
completed | May 10, 2026, 6:18 a.m. |
| PD | Predicate disambiguation | batch_6a0022943fd08190b73007f080d5971d |
completed | May 10, 2026, 6:15 a.m. |
Created at: April 28, 2026, 2:25 p.m.