Triple
T1251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Carnegie |
E24
|
entity |
| Predicate | philanthropicFocus |
P31
|
FINISHED |
| Object | public libraries |
—
|
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: public libraries | Statement: [Andrew Carnegie, philanthropicFocus, public libraries]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: philanthropicFocus Context triple: [Andrew Carnegie, philanthropicFocus, public libraries]
-
A.
nonprofitStatus
Indicates that an entity operates as a nonprofit organization, typically meeting legal or regulatory criteria for nonprofit status.
-
B.
fundedBy
Indicates that an entity receives financial support or resources from another entity.
-
C.
focusesOn
chosen
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
D.
notableFor
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
-
E.
purpose
Indicates that one entity exists, is done, or is used in order to achieve, support, or serve the goal, function, or intended outcome of another entity.
- 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_69a22a285828819081a58308fb963df1 |
completed | Feb. 27, 2026, 11:35 p.m. |
| NER | Named-entity recognition | batch_69a23211f05c8190b8deb03a8540d84d |
completed | Feb. 28, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69a230c2c48481908beb1db3cc9768aa |
completed | Feb. 28, 2026, 12:03 a.m. |
Created at: Feb. 27, 2026, 11:36 p.m.