Triple
T3452621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frankish annals |
E72827
|
entity |
| Predicate | chronologicalStructure |
P15777
|
FINISHED |
| Object | year-by-year record |
—
|
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: year-by-year record | Statement: [Frankish annals, chronologicalStructure, year-by-year record]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chronologicalStructure Context triple: [Frankish annals, chronologicalStructure, year-by-year record]
-
A.
chronologicallyCovers
Indicates that one time period, event, or sequence extends over and includes the entire chronological span of another.
-
B.
chronologicalFunction
chosen
Indicates a temporal relationship where one event or state functions to order, structure, or position another within a sequence of time.
-
C.
chronologicalPosition
Indicates the relative ordering of one event or entity in time with respect to another.
-
D.
chronologyNote
Indicates a note that explains or clarifies the temporal order, dating, or sequence of related events or records.
-
E.
chronologicalOrderInSeries
Indicates that one entity appears earlier or later than another within an ordered sequence or series.
- 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_69ad85b12a908190a1d10a6b03b4f8ae |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbaa2f5ec81909ced93c01e8fe38b |
completed | March 8, 2026, 6:06 p.m. |
| PD | Predicate disambiguation | batch_69adae041d588190a84a02bca94adec8 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:16 p.m.