Triple
T31591404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Library of Ferdinand Columbus |
E806105
|
entity |
| Predicate | goalOfFounder |
P32787
|
FINISHED |
| Object | to own a copy of every book printed |
—
|
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: to own a copy of every book printed | Statement: [Library of Ferdinand Columbus, goalOfFounder, to own a copy of every book printed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: goalOfFounder Context triple: [Library of Ferdinand Columbus, goalOfFounder, to own a copy of every book printed]
-
A.
goalAtFounding
Indicates that an entity had a particular goal or intended purpose at the time it was founded.
-
B.
purposeOfFoundation
chosen
Indicates the reason or intended goal for which an organization, institution, or entity was originally established.
-
C.
founder
Indicates that an entity established, created, or started another entity such as an organization, institution, or company.
-
D.
aimOf
Indicates that one entity serves as the goal, purpose, or intended target of another entity’s action, plan, or existence.
-
E.
aimedToEstablish
Indicates an intention or effort directed toward creating, founding, or setting up something.
- 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_69f348d4891c8190b02bae3c8ecb68b7 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a8316e748190a5362888ba07ee07 |
completed | May 3, 2026, 1:43 a.m. |
| PD | Predicate disambiguation | batch_69f6a75656e081908739ed9e2f600e42 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 30, 2026, 10:28 p.m.