Triple
T611629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Élysée Palace |
E12111
|
entity |
| Predicate | becamePresidentialResidence |
P8952
|
FINISHED |
| Object | 1848 |
—
|
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: 1848 | Statement: [Élysée Palace, becamePresidentialResidence, 1848]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: becamePresidentialResidence Context triple: [Élysée Palace, becamePresidentialResidence, 1848]
-
A.
homeOfPresident
chosen
Indicates the location that serves as the residence of a president.
-
B.
reoccupiedAsGovernorResidenceFrom
Indicates that an entity resumed using a location as the official governor’s residence, starting from a specified prior holder or state.
-
C.
startTimeOfWhiteHouseResidence
Indicates the time at which an entity’s period of residence in the White House begins.
-
D.
reoccupiedAsGovernorResidenceUntil
Indicates that an individual resumed using a residence in their capacity as governor and continued to occupy it in that role until a specified time.
-
E.
servedAsResidenceOf
Indicates that something functioned as the home or dwelling place of a particular person or group.
- 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_69a493309df48190a327f748e88049a6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49e07739481909930a6577c081b9e |
completed | March 1, 2026, 8:13 p.m. |
| PD | Predicate disambiguation | batch_69a49cfa7b4481909bec7a5fd3e98c65 |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.