Triple
T4297193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siscia |
E99742
|
entity |
| Predicate | conqueredInCentury |
P32947
|
FINISHED |
| Object | 1st 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: 1st century BC | Statement: [Siscia, conqueredInCentury, 1st century BC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conqueredInCentury Context triple: [Siscia, conqueredInCentury, 1st century BC]
-
A.
conquestYear
Indicates the year in which one entity successfully conquered or took control over another entity.
-
B.
conquestPeriod
Indicates the time span during which one entity successfully subjugates or takes control of another through conquest.
-
C.
conqueredIn
chosen
Indicates that one entity gained control over another entity or territory as a result of a specific conquest event or campaign.
-
D.
ruledUntilCentury
Indicates that a ruling relationship held by an entity continued in effect up to (but not necessarily including) a specified century.
-
E.
conqueredInPartBy
Indicates that one entity has gained control over a portion, but not the entirety, of another entity through conquest.
- 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_69b3455175088190aa79c6e03b86647e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3509aebd48190af38f2e37f07869a |
completed | March 12, 2026, 11:47 p.m. |
| PD | Predicate disambiguation | batch_69b347fe55a88190b77bab0c0f38e1aa |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:08 p.m.