Triple
T24758136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tolai people |
E619349
|
entity |
| Predicate | usesShellMoneyFor |
P43040
|
FINISHED |
| Object | compensation payments |
—
|
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: compensation payments | Statement: [Tolai people, usesShellMoneyFor, compensation payments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesShellMoneyFor Context triple: [Tolai people, usesShellMoneyFor, compensation payments]
-
A.
usesCurrency
Indicates that one entity conducts its financial transactions or values using the monetary unit represented by the other entity.
-
B.
usedOnDenomination
Indicates that something (such as a material, feature, or design element) is applied to or associated with a particular denomination (e.g., value category of currency or similar units).
-
C.
canWithdrawIntoShell
Indicates that an entity has the ability to retract its body into its shell for protection or concealment.
-
D.
usedFund
chosen
Indicates that one entity expended or applied a particular fund or financial resource for some purpose.
-
E.
usedByDenomination
Indicates that something (such as an object, practice, or concept) is employed or utilized by a particular religious denomination.
- 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_69e2fabbea94819092ed41348909622f |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f5ffc74fa481909b4fe24a9337f9eb |
completed | May 2, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69f5f7f99dc08190afcfb3bc4dfbec1d |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 18, 2026, 4:26 a.m.