Triple
T33329304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Official Records of the War of the Rebellion |
E853357
|
entity |
| Predicate | series2Focus |
P80359
|
FINISHED |
| Object | prisoners of war |
—
|
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: prisoners of war | Statement: [Official Records of the War of the Rebellion, series2Focus, prisoners of war]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: series2Focus Context triple: [Official Records of the War of the Rebellion, series2Focus, prisoners of war]
-
A.
seriesFocus
chosen
Indicates that one entity serves as the primary subject, theme, or focal point of a series created, presented, or organized by another entity.
-
B.
firstSeriesFocusesOn
Indicates that the initial installment or season in a series primarily centers on or is devoted to a particular subject, character, or theme.
-
C.
featuresSeries
Indicates that something includes or presents a particular series as part of its content or offering.
-
D.
seriesBy
Indicates that one entity is the creator, author, or originator of a series to which the other entity belongs.
-
E.
seriesWith
Indicates that one entity is part of, or grouped together in, the same series or sequence as 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_69f34969614c81909cd99661b0902533 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 1, 2026, 1:34 a.m.