Triple
T13325749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman aqueduct |
E317436
|
entity |
| Predicate | typicallyTerminatedIn |
P109534
|
FINISHED |
| Object | castellum divisorium (distribution tank) |
—
|
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: castellum divisorium (distribution tank) | Statement: [Roman aqueduct, typicallyTerminatedIn, castellum divisorium (distribution tank)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyTerminatedIn Context triple: [Roman aqueduct, typicallyTerminatedIn, castellum divisorium (distribution tank)]
-
A.
terminatesOn
Indicates that one process, event, or state causes or marks the ending of another at a specific time or condition.
-
B.
terminatesFor
Indicates that one entity causes or marks the ending or cessation of another entity, process, or state.
-
C.
natureOfTermination
Indicates the manner, cause, or conditions under which a relationship, contract, or employment is brought to an end.
-
D.
terminationInMostStates
Indicates that the relationship or action involves termination that occurs or is valid in the majority of U.S. states.
-
E.
recommendedTerminationOf
Indicates that one party has advised or proposed that another party’s role, contract, or activity should be ended.
- F. None of above. chosen
Provenance (4 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_69d806b4d62c81908d4ced1665414be5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99cfdc9388190af1fdd3cd4717bd8 |
completed | April 11, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69d98f6babd88190a5d529df9584b9a4 |
completed | April 11, 2026, 12:01 a.m. |
| PDg | Predicate description generation | batch_69d99cf7f9c48190a6a4f452b4a2aefa |
completed | April 11, 2026, 12:59 a.m. |
Created at: April 9, 2026, 9:30 p.m.