Triple
T16722273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | McIntyre’s Books |
E406378
|
entity |
| Predicate | hasCuratedSelection |
P113129
|
FINISHED |
| Object | fiction |
—
|
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: fiction | Statement: [McIntyre’s Books, hasCuratedSelection, fiction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCuratedSelection Context triple: [McIntyre’s Books, hasCuratedSelection, fiction]
-
A.
hasSelectionFor
Indicates that one entity holds or specifies a chosen option, subset, or configuration on behalf of another entity.
-
B.
isCurated
chosen
Indicates that an entity has been deliberately selected, organized, or managed according to specific criteria or standards.
-
C.
coCuratedWith
Indicates that two or more entities have been jointly curated or organized together as part of the same curation activity or process.
-
D.
curatedIn
Indicates that an entity has been intentionally selected, organized, or managed for inclusion within a particular collection, exhibition, or curated context.
-
E.
isSelective
Indicates that the relationship or action involves choosing or affecting only certain specific entities or options while excluding others based on particular criteria.
- 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e387449eb08190b174f8e142ea631b |
completed | April 18, 2026, 1:29 p.m. |
| PD | Predicate disambiguation | batch_69e319c379f88190ac0adf812486f598 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:20 a.m.