Triple
T1975402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlantic herring |
E42897
|
entity |
| Predicate | processedAs |
P924
|
FINISHED |
| Object | salted herring |
—
|
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: salted herring | Statement: [Atlantic herring, processedAs, salted herring]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: processedAs Context triple: [Atlantic herring, processedAs, salted herring]
-
A.
usedProcess
chosen
Indicates that an entity employed or applied a particular process to achieve a result or perform an action.
-
B.
constructedAs
Indicates that one entity is built, formed, or created in the manner, structure, or configuration specified by another entity.
-
C.
passed
Indicates that one entity successfully transferred control, responsibility, or an item (such as an object, message, or test) to another entity or through a specified stage or condition.
-
D.
considered
Indicates that one entity regards, judges, or thinks about another entity in a particular way or context.
-
E.
reconstructedAs
Indicates that one entity has been rebuilt, recreated, or inferred based on evidence, models, or partial information from another entity.
- 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_69a8871289048190b00b0d7744b7b2b1 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb3f835108190b0709ccf3a487a96 |
completed | March 7, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69abaff9a09c8190a81fa13f4b85bc79 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:36 p.m.