Triple
T35392899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Place de Clichy metro station |
E1022988
|
entity |
| Predicate | formerLine13Designation |
P17520
|
FINISHED |
| Object | Line B of the Nord-Sud Company |
—
|
NE NERFINISHED |
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: Line B of the Nord-Sud Company | Statement: [Place de Clichy metro station, formerLine13Designation, Line B of the Nord-Sud Company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerLine13Designation Context triple: [Place de Clichy metro station, formerLine13Designation, Line B of the Nord-Sud Company]
-
A.
lineRole_Line13
Indicates that an entity serves a specific role or function within the context of Line 13.
-
B.
formerDesignation
Indicates that an entity previously held a particular title, role, or designation that it no longer holds.
-
C.
formerLineName
chosen
Indicates that the object is a previous or former name by which the referenced line was known.
-
D.
formerLineLetter
Indicates that one entity is a letter that previously belonged to a particular line (such as a transit line or route) but no longer does.
-
E.
formerLine
Indicates that an entity previously served as a particular transit or service line but no longer does so.
- 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_69f76df34ba48190bd80f0814cdcd540 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a0059f4ffe481908dc500cee9051148 |
completed | May 10, 2026, 10:12 a.m. |
| PD | Predicate disambiguation | batch_6a00593a3c1881909b2ff1a29eb474b3 |
completed | May 10, 2026, 10:08 a.m. |
Created at: May 3, 2026, 4:03 p.m.