Triple
T37869952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tagliamento |
E944576
|
entity |
| Predicate | channelPattern |
P189311
|
FINISHED |
| Object | braided channel |
—
|
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: braided channel | Statement: [Tagliamento, channelPattern, braided channel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: channelPattern Context triple: [Tagliamento, channelPattern, braided channel]
-
A.
channelLining
Indicates the presence or application of a protective or functional lining along the interior surface of a channel or conduit.
-
B.
channels
Indicates that one entity serves as a medium, route, or conduit through which another entity is directed, transmitted, or delivered.
-
C.
channelFunction
Indicates that one entity serves as the functional role, purpose, or operational behavior of a channel or conduit associated with another entity.
-
D.
channelStrategy
Indicates how a product, service, or message is planned to be distributed or delivered through specific channels to reach its intended audience.
-
E.
channelAccess
Indicates that one entity has permission or ability to use, view, or interact with a particular communication channel or medium associated with another entity.
- 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_69f76eef55d481908ca6660b4b532550 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbbae559a8819086ef839973f8d9b2 |
completed | May 6, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69fbb1440fa08190abf25ba684f75b6e |
completed | May 6, 2026, 9:23 p.m. |
| PDg | Predicate description generation | batch_69fbbae3fc508190adff3d7abbf107a4 |
completed | May 6, 2026, 10:04 p.m. |
Created at: May 3, 2026, 4:19 p.m.