Triple
T31756244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Puerto Rico Community Survey |
E810561
|
entity |
| Predicate | dataReleaseFormat |
P94056
|
FINISHED |
| Object | summary tables |
—
|
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: summary tables | Statement: [Puerto Rico Community Survey, dataReleaseFormat, summary tables]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataReleaseFormat Context triple: [Puerto Rico Community Survey, dataReleaseFormat, summary tables]
-
A.
dataReleaseDate
Indicates the date on which a particular dataset or piece of data is officially made available or published.
-
B.
dataAvailableAs
chosen
Indicates that specific data can be accessed or obtained in a particular form, format, or representation.
-
C.
dataReleaseAgency
Indicates the agency or organization responsible for releasing or publishing a given set of data.
-
D.
dataPublication
Indicates that some data has been made publicly available or formally released, typically through a defined dissemination or publishing process.
-
E.
typicalReleaseFormat
Indicates the usual or standard format in which something is released or published.
- 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_69f348e340d48190b780fae618c51464 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6ab7cf30c81908c8fd2500c358e83 |
completed | May 3, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:29 p.m.