Triple
T19270893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Slavutych |
E481919
|
entity |
| Predicate | replacedResidenceFor |
P113065
|
FINISHED |
| Object | Pripyat residents |
—
|
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: Pripyat residents | Statement: [Slavutych, replacedResidenceFor, Pripyat residents]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacedResidenceFor Context triple: [Slavutych, replacedResidenceFor, Pripyat residents]
-
A.
laterResidenceShiftOf
Indicates that one residence shift event occurs chronologically after another residence shift event for the same entity.
-
B.
otherResidence
Indicates that an entity has an additional or alternative place of residence beyond its primary home.
-
C.
succeededByResidence
chosen
Indicates that one residence directly follows and replaces another as the primary place of dwelling for an entity.
-
D.
movedPremises
Indicates that an entity has changed its location or base of operations from one set of premises to another.
-
E.
usedAsResidenceAgainBy
Indicates that something previously used as a residence is once more being used as a residence by a particular entity.
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fbb8bea08190b5c65eebe67dccbb |
completed | April 20, 2026, 10:11 a.m. |
| PD | Predicate disambiguation | batch_69e4dd07a7208190afcd51ba1dc87c33 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:29 p.m.