Triple
T6287503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bellerophon |
E140935
|
entity |
| Predicate | receivedItem |
P52361
|
FINISHED |
| Object | tablet with sealed message from Proetus to Iobates |
—
|
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: tablet with sealed message from Proetus to Iobates | Statement: [Bellerophon, receivedItem, tablet with sealed message from Proetus to Iobates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: receivedItem Context triple: [Bellerophon, receivedItem, tablet with sealed message from Proetus to Iobates]
-
A.
receivedFor
Indicates that something was obtained, accepted, or taken into possession on behalf of or for the benefit of a specified entity.
-
B.
receivedForWork
Indicates that something was obtained or accepted as compensation or reward in exchange for performing work or services.
-
C.
receivedPromiseAbout
Indicates that one entity has been given an assurance or commitment concerning another entity or event by some source.
-
D.
receivedSupportFrom
Indicates that one entity obtained help, resources, or backing from another entity.
-
E.
recipientOf
chosen
Indicates that one entity is the receiver or beneficiary of something (such as an item, message, or action) from 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_69c008cd17c8819082b82d3fbeb68047 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063ff9f74819088dc603f56fc930c |
completed | March 22, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69c0560a0270819098ad2785b91e8f39 |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:26 p.m.