Triple
T10191225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château de Versailles |
E238037
|
entity |
| Predicate | seatOfGovernmentUntil |
P13207
|
FINISHED |
| Object | 1789 |
—
|
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: 1789 | Statement: [Château de Versailles, seatOfGovernmentUntil, 1789]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seatOfGovernmentUntil Context triple: [Château de Versailles, seatOfGovernmentUntil, 1789]
-
A.
laterSeatOfGovernment
Indicates that the referenced place served as a subsequent seat of government for the same political entity after an earlier one.
-
B.
seatOfGovernment
Indicates that a location serves as the administrative center where a government exercises its official authority and conducts its primary governing functions.
-
C.
governingSince
Indicates that one entity has held a governing or ruling role over another entity starting from a specified point in time.
-
D.
servedAsNationalCapitalUntil
chosen
Indicates that a place functioned as the national capital of a country or state up to a specified end date, after which it no longer held that status.
-
E.
servedAsUSCapitalUntil
Indicates that a place functioned as the capital of the United States up to a specified end date.
- 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_69ca84de1b208190bf17bb305b002605 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cded7eb1148190a2d175163685e233 |
completed | April 2, 2026, 4:15 a.m. |
| PD | Predicate disambiguation | batch_69cd7c8477648190bc55c56aeec507d3 |
completed | April 1, 2026, 8:13 p.m. |
Created at: March 30, 2026, 9:13 p.m.