Triple
T35490233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unification War |
E1025712
|
entity |
| Predicate | timeRelativeToSeries |
P55209
|
FINISHED |
| Object | occurs several years before events of Firefly |
—
|
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: occurs several years before events of Firefly | Statement: [Unification War, timeRelativeToSeries, occurs several years before events of Firefly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeRelativeToSeries Context triple: [Unification War, timeRelativeToSeries, occurs several years before events of Firefly]
-
A.
timeInSeries
Indicates that one temporal value occurs within the duration or sequence span defined by another in a series.
-
B.
timePeriodInSeries
Indicates the specific time span or interval during which an installment, episode, or part occurs within a larger series or sequence.
-
C.
timeIndexed
Indicates that the relationship or property it connects is associated with, or valid during, a specific time or time interval.
-
D.
timeScaleComparedTo
Indicates how the temporal scale or duration of one entity or process relates to that of another (e.g., faster, slower, longer, shorter, or at a different granularity).
-
E.
dateRelativeTo
chosen
Indicates a temporal relationship where one date is defined, positioned, or interpreted in relation to another reference date (e.g., before, after, or offset by a specific duration).
- 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_69f76dfbcdd881908c7b0b6bc502252b |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:04 p.m.