Triple
T36121379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tithraustes |
E1044750
|
entity |
| Predicate | paidToAgesilaus |
P72734
|
FINISHED |
| Object | money to finance Spartan campaigns in Greece |
—
|
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: money to finance Spartan campaigns in Greece | Statement: [Tithraustes, paidToAgesilaus, money to finance Spartan campaigns in Greece]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paidToAgesilaus Context triple: [Tithraustes, paidToAgesilaus, money to finance Spartan campaigns in Greece]
-
A.
paidBy
Indicates that a payment or financial obligation is made or settled by the specified entity.
-
B.
paidFor
Indicates that one entity provided payment to cover the cost of something on behalf of another entity.
-
C.
paysAfter
Indicates that one entity makes a payment to another entity only after a specified event, condition, or time has occurred.
-
D.
previouslyPaidTo
chosen
Indicates that a payment was made in the past from one entity to another.
-
E.
payAndRations
Indicates the provision of both monetary compensation and subsistence support (such as food or basic supplies) to an individual, typically in an employment or service context.
- 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_69f76e356c908190abc6ca1e6a05b011 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b3e2f3c08190be4fd1ae4fa1266d |
completed | May 3, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bcc47081909fe7d592ac69006c |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:08 p.m.