Triple
T12884737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Floss |
E308196
|
entity |
| Predicate | hasFeatureInStory |
P106216
|
FINISHED |
| Object | waterway used for milling |
—
|
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: waterway used for milling | Statement: [River Floss, hasFeatureInStory, waterway used for milling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFeatureInStory Context triple: [River Floss, hasFeatureInStory, waterway used for milling]
-
A.
hasThemeInStory
Indicates that a particular theme is present or plays a significant role within a given story.
-
B.
hasFeatureInFiction
chosen
Indicates that a fictional work includes or portrays a particular feature, trait, or characteristic.
-
C.
hasSiblingInStory
Indicates that one character in a narrative has at least one sibling who also appears within the same story.
-
D.
hasAwardInStory
Indicates that an entity is depicted within a narrative or story as having received a particular award.
-
E.
hasFandomWithinStory
Indicates that within the narrative of a story, one entity is a fan or admirer of another entity (such as a character, group, or work) that exists inside that same story world.
- 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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97c7f91d08190aac2f6419d3ba992 |
completed | April 10, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69d96fa55b888190ab1612e93c41aec4 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:39 p.m.