Triple
T3698583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grand Prix de Rome in architecture |
E78517
|
entity |
| Predicate | residenceDuration |
P43829
|
FINISHED |
| Object | several years |
—
|
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: several years | Statement: [Grand Prix de Rome in architecture, residenceDuration, several years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: residenceDuration Context triple: [Grand Prix de Rome in architecture, residenceDuration, several years]
-
A.
mainResidencePeriod
chosen
Indicates the time span during which a particular place serves as an entity’s primary or main residence.
-
B.
yearOfPermanentResidency
Indicates the specific year in which an entity began or was granted permanent residency in a particular place.
-
C.
periodOfResidenceStart
Indicates the date or point in time when an entity’s period of residence at a particular place begins.
-
D.
endDateOfResidence
Indicates the date on which a particular period of residence at a location comes to an end.
-
E.
periodOfContinuousInhabitation
Indicates a span of time during which a place is continuously inhabited without interruption.
- 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_69ad85e3b1888190abc983e06968696d |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc512ba188190a15bcacafac3f476 |
completed | March 8, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_69adb84dc5808190850aa6975cb09e27 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:26 p.m.