Triple
T31368859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Selma Ježková |
E800089
|
entity |
| Predicate | savesMoneyFor |
P157541
|
FINISHED |
| Object | Gene’s medical operation |
—
|
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: Gene’s medical operation | Statement: [Selma Ježková, savesMoneyFor, Gene’s medical operation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: savesMoneyFor Context triple: [Selma Ježková, savesMoneyFor, Gene’s medical operation]
-
A.
savingsDoNotCountAgainst
Indicates that the specified savings are excluded from consideration or calculation in a particular limit, threshold, or eligibility assessment.
-
B.
earnOn
Indicates that one entity gains income, profit, or returns as a result of another entity or activity.
-
C.
incomeUsedFor
Indicates that some or all of an income amount is allocated or spent for a specified purpose, activity, or recipient.
-
D.
economicGoal
Indicates that an entity has a targeted economic outcome or objective it aims to achieve.
-
E.
usesWealthFor
chosen
Indicates that one entity directs or allocates its wealth or financial resources toward another entity or purpose.
- 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_69f224e6b7448190ac6bf97ad7364160 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69f88006c81909440631225f38c04 |
completed | May 3, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69f69d1d25e88190a7f57d323574da90 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:18 p.m.