Triple
T37277055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A-1 |
E924673
|
entity |
| Predicate | relativeOrderOnLine |
P37518
|
FINISHED |
| Object | first station on Line M1 from the 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: first station on Line M1 from the south | Statement: [A-1, relativeOrderOnLine, first station on Line M1 from the south]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeOrderOnLine Context triple: [A-1, relativeOrderOnLine, first station on Line M1 from the south]
-
A.
orderOf
chosen
Indicates that one entity is arranged, ranked, or sequenced before or after another according to a specified ordering criterion.
-
B.
linkedOrder
Indicates that one order is associated with or connected to another order in a defined relationship.
-
C.
confersOrder
Indicates that one entity formally bestows or grants an order, rank, or honorific distinction upon another entity.
-
D.
relativePositioning
Indicates how one entity is spatially arranged or located in relation to another entity.
-
E.
joinedOrderOf
Indicates that an entity became a member of, or formally joined, a particular order or organization.
- 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_69f76eacdd8c819094080d3991e6d37c |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:16 p.m.