Triple
T37560020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris to the Past: Traveling through French History by Train |
E933791
|
entity |
| Predicate | startingPointOfJourneys |
P27471
|
FINISHED |
| Object | Paris |
—
|
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: Paris | Statement: [Paris to the Past: Traveling through French History by Train, startingPointOfJourneys, Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startingPointOfJourneys Context triple: [Paris to the Past: Traveling through French History by Train, startingPointOfJourneys, Paris]
-
A.
tourStartingPoint
Indicates the location or point from which a tour begins.
-
B.
journeyFrom
chosen
Indicates that an entity undertakes or originates a journey starting from a specified location or source.
-
C.
startPoint
Indicates the initial location or position from which an object, path, or action begins.
-
D.
pilgrimageStartingPoint
Indicates the location from which a pilgrimage journey is initiated or begins.
-
E.
journeyDestination
Indicates that one entity serves as the endpoint or intended destination of another entity’s journey or travel.
- 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_69f76ecb4acc8190b53f96d0b013e415 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0127c36dc08190b07765756b3d0e1b |
completed | May 11, 2026, 12:50 a.m. |
| PD | Predicate disambiguation | batch_6a0125ef57208190be5b5e761fcae981 |
completed | May 11, 2026, 12:42 a.m. |
Created at: May 3, 2026, 4:17 p.m.