Triple
T12150746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tuileries metro station |
E289444
|
entity |
| Predicate | hasAutomationStatus |
P11174
|
FINISHED |
| Object | served by automated trains on Line 1 |
—
|
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: served by automated trains on Line 1 | Statement: [Tuileries metro station, hasAutomationStatus, served by automated trains on Line 1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAutomationStatus Context triple: [Tuileries metro station, hasAutomationStatus, served by automated trains on Line 1]
-
A.
automationStatus
chosen
Indicates whether a process, task, or system is being performed automatically or requires manual intervention.
-
B.
canAutomate
Indicates that one entity has the capability to perform, control, or execute another entity’s process or task automatically without continuous human intervention.
-
C.
automatedIn
Indicates that an action, process, or operation is performed automatically within or by a specified system, context, or environment.
-
D.
hasEquipmentStatus
Indicates the current operational or condition state assigned to a piece of equipment.
-
E.
hasModelStatus
Indicates that an entity is assigned a particular model-related state or condition, such as its current phase, validity, or operational status within a modeling context.
- 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_69d6ab4c6710819097a9d228382dde43 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915d7109481908bf5fe512bba3c89 |
completed | April 10, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69d9150c18148190bf8152189c0e5fca |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:49 p.m.