Triple
T35791629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cassiel |
E1034706
|
entity |
| Predicate | positionInStoryWorld |
P198764
|
FINISHED |
| Object | on the margins of human society |
—
|
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: on the margins of human society | Statement: [Cassiel, positionInStoryWorld, on the margins of human society]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInStoryWorld Context triple: [Cassiel, positionInStoryWorld, on the margins of human society]
-
A.
positionInStory
Indicates the point or role an event, character, or element occupies within the overall sequence or structure of a story.
-
B.
positionInWorlds
Indicates that an entity occupies specific spatial coordinates or locations within one or more distinct worlds or environments.
-
C.
positionHeldInNarrative
chosen
Indicates that one entity holds a specific role, status, or position within the structure or storyline of a narrative.
-
D.
positionInFrame
Indicates the spatial location or coordinates of an entity within a specific frame or reference image.
-
E.
positionOnSystem
Indicates the relative location or placement of an entity within a larger structured system or framework.
- 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_69f76e1575908190aaa306d843b41c14 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff878f41888190bcb3bc41ad26081a |
completed | May 9, 2026, 7:14 p.m. |
| PD | Predicate disambiguation | batch_69ff854082d88190aad3bfedf05e849f |
completed | May 9, 2026, 7:04 p.m. |
Created at: May 3, 2026, 4:06 p.m.