Triple
T15352363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Los Angeles River Viaducts |
E367084
|
entity |
| Predicate | spanFeature |
P118226
|
FINISHED |
| Object | Los Angeles River 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: Los Angeles River channel | Statement: [Los Angeles River Viaducts, spanFeature, Los Angeles River channel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spanFeature Context triple: [Los Angeles River Viaducts, spanFeature, Los Angeles River channel]
-
A.
linguisticFeature
Indicates a relationship where a linguistic property, pattern, or characteristic is attributed to or associated with a language-related entity (such as a word, phrase, or text).
-
B.
statementFeature
Indicates that a statement possesses a particular characteristic, attribute, or quality that distinguishes it from other statements.
-
C.
spanType
Indicates the specific category or kind of span that characterizes the relationship or action between entities.
-
D.
markingFeature
Indicates a feature that serves as a distinguishing mark or identifier associated with an entity.
-
E.
stylingFeature
Indicates a visual or design-related characteristic applied to an entity, such as formatting, layout, or aesthetic treatment.
- 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_69d85a1355608190a6673ddb67231d54 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e290efc8190b22c95dcd3e5f57f |
completed | April 16, 2026, 1:40 a.m. |
| PD | Predicate disambiguation | batch_69deca991e5081908b0df3d1ee7d5338 |
completed | April 14, 2026, 11:15 p.m. |
| PDg | Predicate description generation | batch_69decf2e413481909d9180a8d78d2c17 |
completed | April 14, 2026, 11:35 p.m. |
Created at: April 10, 2026, 3:17 a.m.