Triple
T23144339
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Navroz |
E577544
|
entity |
| Predicate | observedOnCalendar |
P1818
|
FINISHED |
| Object | solar calendar |
—
|
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: solar calendar | Statement: [Navroz, observedOnCalendar, solar calendar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: observedOnCalendar Context triple: [Navroz, observedOnCalendar, solar calendar]
-
A.
dateObserved
Indicates the specific date on which an event, condition, or measurement was recorded or observed.
-
B.
usesCalendar
chosen
Indicates that an entity employs or relies on a calendar system for organizing, tracking, or scheduling dates and events.
-
C.
alsoObservedOn
Indicates that the same entity, event, or phenomenon was additionally observed on another occasion, date, or context beyond the primary one referenced.
-
D.
observedWhen
Indicates that one entity is observed or recorded at a specific time or under particular temporal conditions.
-
E.
isObservedOn
Indicates that a particular phenomenon, condition, or attribute is detected or recorded at a specific time, date, or occasion.
- 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_69e245f8e6248190ba3d58e068b4dccb |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ecd40108190aaad7faf754b7936 |
completed | April 29, 2026, 4:53 a.m. |
| PD | Predicate disambiguation | batch_69ef89f83b108190aaaa1db6221fc163 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:01 p.m.