Triple
T9922796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of the American Republic, Paris Exposition of 1900 (temporary building) |
E187840
|
entity |
| Predicate | expositionOpeningYear |
P30542
|
FINISHED |
| Object | 1900 |
—
|
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: 1900 | Statement: [House of the American Republic, Paris Exposition of 1900 (temporary building), expositionOpeningYear, 1900]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: expositionOpeningYear Context triple: [House of the American Republic, Paris Exposition of 1900 (temporary building), expositionOpeningYear, 1900]
-
A.
yearExhibited
Indicates the specific year in which an entity (such as an artwork, object, or performance) was publicly exhibited or displayed.
-
B.
yearOpenedToPublic
Indicates the calendar year in which something (such as a place, facility, or service) was first made accessible to the general public.
-
C.
exhibitionStartDate
chosen
Indicates the date on which an exhibition begins or is first opened to the public.
-
D.
officialOpeningYear
Indicates the calendar year in which something was formally opened or inaugurated for official use.
-
E.
openedAsMuseumIn
Indicates that a place or building began operating as a museum in a specified year or at a specified time.
- 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_69ca82b22a688190b52c75bd48429c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb56c7da88190ac37986a2e766b1e |
completed | April 2, 2026, 12:16 a.m. |
| PD | Predicate disambiguation | batch_69cd1d90b8a8819081748f129c0c6ab6 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:42 p.m.