Triple
T22137405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Large Two Forms |
E547065
|
entity |
| Predicate | voids |
P147127
|
FINISHED |
| Object | large openings between forms |
—
|
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: large openings between forms | Statement: [Large Two Forms, voids, large openings between forms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: voids Context triple: [Large Two Forms, voids, large openings between forms]
-
A.
vise
Indicates that one entity firmly grips, clamps, or holds another in place, typically restricting its movement or separating it from other objects.
-
B.
with
Indicates a general associative relationship in which one entity is accompanied by, connected to, or occurring together with another entity.
-
C.
seos
Indicates a search engine optimization (SEO) relationship, where one entity improves or influences the visibility, ranking, or discoverability of another in search results.
-
D.
by
Indicates that an action is performed, caused, or authored through the agency, means, or proximity of a specified entity.
-
E.
among
Indicates that one or more entities are considered as part of, or in relation to, a larger group or collection of entities.
- 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_69e11e3a95d88190a3bd80d9471976c3 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129bb78bc8190b74af3a5f6a5348f |
completed | April 28, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69e71b384e008190b723c9a0f1089d66 |
completed | April 21, 2026, 6:37 a.m. |
| PDg | Predicate description generation | batch_69e7222d208c819098b12c13e31af629 |
completed | April 21, 2026, 7:07 a.m. |
Created at: April 16, 2026, 8:32 p.m.