Triple
T33035495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arga-Sala River |
E845297
|
entity |
| Predicate | frozenFor |
P176385
|
FINISHED |
| Object | most of the year |
—
|
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: most of the year | Statement: [Arga-Sala River, frozenFor, most of the year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frozenFor Context triple: [Arga-Sala River, frozenFor, most of the year]
-
A.
frozenOn
Indicates that one entity becomes immobile or inactive at a specific time, event, or condition, as if stopped or preserved in its current state.
-
B.
frozenIn
Indicates that one entity is immobilized or preserved in a solid, frozen state within or by another entity.
-
C.
frozenFrom
Indicates that one entity has been preserved or immobilized by being frozen starting from another entity, source, or prior state.
-
D.
assetsFrozenBy
Indicates that one party has restricted or immobilized another party’s assets, preventing their use or transfer.
-
E.
frozenInMotion
Indicates that an entity is captured or held at a specific point within an ongoing action or movement, as if paused mid-motion.
- 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_69f34951348c8190b56746b0a7018182 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6e02ba6b881908dfafc52d3b75f1c |
completed | May 3, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69f6de09c2f481909f8b2545d3208c9f |
completed | May 3, 2026, 5:32 a.m. |
| PDg | Predicate description generation | batch_69f6e029f0f88190b1f88d82a4a2cabd |
completed | May 3, 2026, 5:42 a.m. |
Created at: May 1, 2026, 1:24 a.m.