Triple
T2391623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palace of Culture and Science |
E48955
|
entity |
| Predicate | clockInstallationYear |
P37139
|
FINISHED |
| Object | 2000 |
—
|
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: 2000 | Statement: [Palace of Culture and Science, clockInstallationYear, 2000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clockInstallationYear Context triple: [Palace of Culture and Science, clockInstallationYear, 2000]
-
A.
yearOfOriginalInstallation
Indicates the specific calendar year when something was first installed or put into initial operation.
-
B.
yearOfOrganInstallation
Indicates the year in which an organ was installed at a particular location or in a particular instrument.
-
C.
clockMechanismCompletedInYear
chosen
Indicates that the construction or completion of a clock mechanism occurred in a specified year.
-
D.
clockType
Indicates the type or category of a clock associated with an entity (e.g., analog, digital, system clock, etc.).
-
E.
hasClockTower
Indicates that one entity possesses or features a clock tower as part of its structure or property.
- 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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc87587708190a7f2bc473a898bc2 |
completed | March 7, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69abc5a1b5748190b4cd8989700f4dd2 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:57 p.m.