Triple
T1255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Carnegie |
E24
|
entity |
| Predicate | funded |
P67
|
FINISHED |
| Object | construction of Carnegie libraries across the English-speaking world |
—
|
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: construction of Carnegie libraries across the English-speaking world | Statement: [Andrew Carnegie, funded, construction of Carnegie libraries across the English-speaking world]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: funded Context triple: [Andrew Carnegie, funded, construction of Carnegie libraries across the English-speaking world]
-
A.
fundedBy
chosen
Indicates that an entity receives financial support or resources from another entity.
-
B.
fundingModel
Indicates how an entity is financially supported or sustained, such as through specific revenue sources, payment structures, or funding mechanisms.
-
C.
developed
Indicates that one entity created, designed, or brought another entity into a more advanced or complete state through effort or work.
-
D.
influenced
Indicates that one entity has affected, shaped, or altered another entity’s state, behavior, or characteristics.
-
E.
submittedTo
Indicates that one entity has formally sent or presented something (such as a document, request, or work) to another entity for consideration, review, or processing.
- 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.