Triple
T15152966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tagish language |
E361994
|
entity |
| Predicate | preservationFormat |
P117530
|
FINISHED |
| Object | audio recordings |
—
|
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: audio recordings | Statement: [Tagish language, preservationFormat, audio recordings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preservationFormat Context triple: [Tagish language, preservationFormat, audio recordings]
-
A.
preservationType
Indicates the method or process by which something is preserved or kept from deterioration.
-
B.
storageFormat
Indicates the specific way in which data or content is physically or logically organized, encoded, and stored.
-
C.
preservationMethod
Indicates the technique or process used to maintain, protect, or prolong the condition, quality, or usability of something over time.
-
D.
presentedInFormat
Indicates that something is expressed, delivered, or made available using a particular format or representation.
-
E.
mediaTypePreserved
Indicates that the original media type or format of an item has been maintained without alteration.
- F. None of above. chosen
Provenance (4 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_69d85a0759908190b8a051d2e2a1cbe6 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00609040081908c849475a2fa6443 |
completed | April 15, 2026, 9:41 p.m. |
| PD | Predicate disambiguation | batch_69deb9779acc81908ed2dad382c42dca |
completed | April 14, 2026, 10:02 p.m. |
| PDg | Predicate description generation | batch_69dec71e8dcc81908badc834b6ccf273 |
completed | April 14, 2026, 11 p.m. |
Created at: April 10, 2026, 3:07 a.m.