Triple
T20684083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Centennial Exposition |
E508368
|
entity |
| Predicate | anniversaryCelebrated |
P80485
|
FINISHED |
| Object | centennial of the United States |
—
|
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: centennial of the United States | Statement: [Centennial Exposition, anniversaryCelebrated, centennial of the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: anniversaryCelebrated Context triple: [Centennial Exposition, anniversaryCelebrated, centennial of the United States]
-
A.
anniversaryOf
chosen
Indicates that one event or date marks the commemoration or yearly recurrence of another specific event.
-
B.
anniversaryNumber
Indicates the specific ordinal count of an anniversary occurrence in a recurring commemorative event or relationship.
-
C.
signedOnAnniversaryOf
Indicates that an agreement or document was signed on the anniversary date of a specific prior event or reference point.
-
D.
typeOfAnniversary
Indicates the specific category or kind of anniversary that an event or date represents (e.g., wedding, work, founding).
-
E.
completionAnniversary
Indicates the date or event marking the anniversary of when something was originally completed.
- 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6beaae5608190ac8cc64aa4717d53 |
completed | April 21, 2026, 12:02 a.m. |
| PD | Predicate disambiguation | batch_69e5c03caee881908be4dd25796a03d5 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 11:45 a.m.