Triple
T14462991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chronicle of Hydatius |
E358631
|
entity |
| Predicate | chronologicalSystemUsed |
P88531
|
FINISHED |
| Object | Anno Mundi |
—
|
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: Anno Mundi | Statement: [Chronicle of Hydatius, chronologicalSystemUsed, Anno Mundi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chronologicalSystemUsed Context triple: [Chronicle of Hydatius, chronologicalSystemUsed, Anno Mundi]
-
A.
chronologyUsedBy
Indicates that a particular system, method, or scheme of chronological ordering is employed or adopted by a given entity.
-
B.
chronologyType
chosen
Indicates the type or system of chronological ordering or dating applied to an event, period, or sequence.
-
C.
usesJulianCalendar
Indicates that the subject follows or is based on the Julian calendar system for dating events or timekeeping.
-
D.
chronologyEstablishedBy
Indicates that the temporal order or dating of events, objects, or periods is determined or defined by a specified source, method, or authority.
-
E.
relativeChronology
Indicates a temporal ordering relationship that specifies how one event or state is positioned in time relative to another (e.g., earlier, later, or overlapping).
- 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_69d82794dfa081909b9134ad2e32244b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91ad67bc81908ecdaa7262f6dc55 |
completed | April 14, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69de5c42bd3c81909a62acf30cc24d1e |
completed | April 14, 2026, 3:24 p.m. |
Created at: April 10, 2026, 1:19 a.m.