Triple
T13325740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman aqueduct |
E317436
|
entity |
| Predicate | firstBuiltAround |
P14056
|
FINISHED |
| Object | 4th century BC |
—
|
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: 4th century BC | Statement: [Roman aqueduct, firstBuiltAround, 4th century BC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstBuiltAround Context triple: [Roman aqueduct, firstBuiltAround, 4th century BC]
-
A.
originallyBuilt
Indicates that one entity was the first or initial builder or constructor of another entity.
-
B.
wasFirstBuiltInYear
Indicates that the initial construction of an entity was completed in a specified year.
-
C.
createdAround
chosen
Indicates that something was brought into existence or produced approximately at a particular time or within an imprecise time period.
-
D.
originallyBuiltUnder
Indicates that something was first constructed during the rule, authority, or administration of a particular person, group, or regime.
-
E.
firstUsedOn
Indicates the date, time, or context in which something was initially applied, activated, or put into use on a particular object or 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_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. |
Created at: April 9, 2026, 9:30 p.m.