Triple
T2013508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swans Reflecting Elephants |
E43740
|
entity |
| Predicate | foreground |
P1699
|
FINISHED |
| Object | lake with swans |
—
|
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: lake with swans | Statement: [Swans Reflecting Elephants, foreground, lake with swans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foreground Context triple: [Swans Reflecting Elephants, foreground, lake with swans]
-
A.
front
chosen
Indicates that one entity is located directly before or facing another entity along a primary viewing or movement direction.
-
B.
primaryFront
Indicates that one entity serves as the main or most important front-facing side or surface in relation to another entity.
-
C.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
D.
frontAffected
Indicates that an action, event, or condition primarily impacts the front side or front-facing part of an entity.
-
E.
frontAssignment
Indicates that one entity is assigned or positioned at the front relative to another entity or context.
- 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_69a88716e9f08190946313fdc949e3cf |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8b42d508190bf2b63132bb2ad77 |
completed | March 7, 2026, 5:33 a.m. |
| PD | Predicate disambiguation | batch_69abb7a03a1c81909ad50d56667db2d5 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:37 p.m.