Triple
T27247388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oglala, South Dakota |
E687380
|
entity |
| Predicate | previousCountyName |
P65436
|
FINISHED |
| Object | Shannon County |
—
|
NE NERFINISHED |
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: Shannon County | Statement: [Oglala, South Dakota, previousCountyName, Shannon County]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousCountyName Context triple: [Oglala, South Dakota, previousCountyName, Shannon County]
-
A.
previousCounty
chosen
Indicates that one county was the immediately preceding county associated with an entity before the current or later county.
-
B.
hasFormerCounty
Indicates that an entity was previously part of, or administered by, a particular county in the past but no longer is.
-
C.
countyName
Indicates the specific name assigned to a county in which an entity is located or with which it is associated.
-
D.
homeCounty
Indicates that a specified county is the primary home or place of residence for a given person or entity.
-
E.
subsequentCounty
Indicates that one county follows another in a defined sequence, such as chronological order of creation or administrative succession.
- 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_69ef355547408190b5ca0d777c65040a |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f7cec454a88190a9f3bbee2b856636 |
completed | May 3, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69f7c8977c288190997a892ec5f756ed |
completed | May 3, 2026, 10:13 p.m. |
Created at: April 27, 2026, 10:42 a.m.