Triple
T23946094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harpsichord |
E602916
|
entity |
| Predicate | isNonPortable |
P57891
|
FINISHED |
| Object | Generally true |
—
|
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: Generally true | Statement: [Harpsichord, isNonPortable, Generally true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isNonPortable Context triple: [Harpsichord, isNonPortable, Generally true]
-
A.
isPortable
chosen
Indicates that an object can be easily moved or carried from one place to another without significant effort or setup.
-
B.
isLessPortableThan
Indicates that one entity is more difficult to move, carry, or transport than another entity.
-
C.
isPortableComparedTo
Indicates that one entity can be moved, carried, or transported more easily than another entity.
-
D.
portabilityConcern
Indicates a relationship where an entity is associated with issues, risks, or considerations about how easily it can be moved, transferred, or used across different environments or contexts.
-
E.
portabilityMethod
Indicates the method or mechanism by which something can be transferred or moved from one context, system, or location to another.
- 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_69e2953e4924819093f1c24c03476b42 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d02dd0cc8190b32eb86bdfe0bf9a |
completed | April 29, 2026, 9:32 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:13 p.m.