Triple
T24600261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1870 United States census |
E608802
|
entity |
| Predicate | firstCensusAfterEvent |
P156707
|
FINISHED |
| Object | American Civil War |
—
|
NE NERFINISHED |
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: American Civil War | Statement: [1870 United States census, firstCensusAfterEvent, American Civil War]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstCensusAfterEvent Context triple: [1870 United States census, firstCensusAfterEvent, American Civil War]
-
A.
createdAfterCensus
Indicates that one entity was created at a point in time later than the date or period of a specified census.
-
B.
occursBetweenCensuses
Indicates that an event or state takes place in the time interval between two consecutive census dates.
-
C.
firstMajorEventAt
Indicates that the referenced event is the earliest major event associated with the given entity, specifying when that first significant occurrence takes place.
-
D.
firstElectionAfter
Indicates that one election is the earliest election that occurs after another specified election.
-
E.
firstMajorEventYear
Indicates the calendar year in which the entity’s first major event occurred.
- 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_69e2c4cf54248190af7b0c2d9ade9830 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6ca751c8190a040c10d701ecf3a |
completed | April 30, 2026, 12:48 a.m. |
| PDg | Predicate description generation | batch_69f2b8b8bc5881908df49c0b07110246 |
completed | April 30, 2026, 2:04 a.m. |
Created at: April 18, 2026, 2:30 a.m.