Triple
T19791583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pont de Mirabeau |
E475423
|
entity |
| Predicate | relie |
P137341
|
FINISHED |
| Object | rive gauche de la Seine |
—
|
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: rive gauche de la Seine | Statement: [Pont de Mirabeau, relie, rive gauche de la Seine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relie Context triple: [Pont de Mirabeau, relie, rive gauche de la Seine]
-
A.
relief
Indicates a state or action in which distress, pain, or difficulty is reduced, eased, or removed for an entity.
-
B.
relievedBy
Indicates that one entity eases, reduces, or removes the burden, pain, stress, or responsibility experienced by another entity.
-
C.
relives
Indicates that one entity experiences again or re-experiences a past event, situation, or emotion associated with another entity.
-
D.
relinquished
Indicates that one entity voluntarily gave up possession, control, or claim over something to another entity or to no one.
-
E.
hasRelief
Indicates that one entity features or exhibits a raised or sculpted surface design (relief) in relation to another entity or context.
- F. None of above. chosen
Provenance (4 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653c37a3c819080f195d58adaaa7b |
completed | April 20, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69e53053ed2881908400becdfada7fd3 |
completed | April 19, 2026, 7:43 p.m. |
| PDg | Predicate description generation | batch_69e532bcf41c8190b685b5adf46a60fc |
completed | April 19, 2026, 7:53 p.m. |
Created at: April 10, 2026, 1:49 p.m.