Triple
T28405153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Impératrice des Français |
E719506
|
entity |
| Predicate | firstHolderCoronationPlace |
P20004
|
FINISHED |
| Object | Notre-Dame de 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: Notre-Dame de Paris | Statement: [Impératrice des Français, firstHolderCoronationPlace, Notre-Dame de Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstHolderCoronationPlace Context triple: [Impératrice des Français, firstHolderCoronationPlace, Notre-Dame de Paris]
-
A.
firstCoronationHeld
Indicates that the referenced coronation event is the earliest (first in time) coronation associated with the given entity.
-
B.
firstCoronationHeldFor
Indicates that a particular entity was the subject or beneficiary of the first coronation event associated with another entity.
-
C.
capitalOfCoronationCountryAtTime
Indicates that a city served as the capital of a specified country at the time when a particular coronation took place.
-
D.
capitalOfCoronationEmpire
Indicates that a city or location serves as the capital of the Coronation Empire.
-
E.
coronationSite
chosen
Indicates the place where a coronation ceremony for a person (typically a monarch) took or takes place.
- 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_69eff6efd1b08190ae3cefd4f11388a2 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_6a000be59ad88190a6aa3a42c097796d |
completed | May 10, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_6a000ab6e9bc81908300b81d004e5921 |
completed | May 10, 2026, 4:33 a.m. |
Created at: April 28, 2026, 1:22 a.m.