Triple
T27473690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zaraysk |
E693391
|
entity |
| Predicate | kremlinBuiltInCentury |
P93743
|
FINISHED |
| Object | 16th century |
—
|
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: 16th century | Statement: [Zaraysk, kremlinBuiltInCentury, 16th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: kremlinBuiltInCentury Context triple: [Zaraysk, kremlinBuiltInCentury, 16th century]
-
A.
fortressWallBuiltInCentury
Indicates that a fortress wall was constructed during a specified century.
-
B.
containsBuildingFromCentury
chosen
Indicates that a location or area includes at least one building that originates from a specified century.
-
C.
rebuiltInCentury
Indicates that an existing structure or entity was reconstructed or significantly rebuilt during a specified century.
-
D.
estimatedConstructionEndCentury
Indicates the century in which the construction of something is estimated to have been completed.
-
E.
constructionOfDomeStartYear
Indicates the calendar year in which the construction of a dome began.
- 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_69ef538105548190a771cc5a0cf8c211 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62e422e7c8190a256e3155a22ba27 |
completed | May 2, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 12:55 p.m.