Triple
T36291881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line A (Nord-Sud) |
E893250
|
entity |
| Predicate | formerOperatorType |
P16344
|
FINISHED |
| Object | private company |
—
|
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: private company | Statement: [Line A (Nord-Sud), formerOperatorType, private company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerOperatorType Context triple: [Line A (Nord-Sud), formerOperatorType, private company]
-
A.
formerOperates
Indicates that an entity previously operated or managed another entity but no longer does so.
-
B.
typicalOperatorType
Indicates the usual or most common type or category of operator associated with a given entity or context.
-
C.
predecessorOperator
Indicates that one operator precedes another in an ordered sequence or process.
-
D.
initialOperator
Indicates that an entity serves as the first or primary operator initiating a process, action, or operation involving another entity.
-
E.
formerType
chosen
Indicates that one entity previously had a certain type, role, or classification but no longer does.
- 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_69f76e4a61f0819084a2b68dbbb4efc6 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a008ebb22408190a2293bced40a7e53 |
completed | May 10, 2026, 1:57 p.m. |
| PD | Predicate disambiguation | batch_6a008e8715dc8190ab23292605901bf4 |
completed | May 10, 2026, 1:56 p.m. |
Created at: May 3, 2026, 4:09 p.m.