Triple
T11547352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ardenweald |
E273804
|
entity |
| Predicate | timeOfDayAppearance |
P6019
|
FINISHED |
| Object | perpetual night |
—
|
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: perpetual night | Statement: [Ardenweald, timeOfDayAppearance, perpetual night]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfDayAppearance Context triple: [Ardenweald, timeOfDayAppearance, perpetual night]
-
A.
timeOfDayCoverage
Indicates the specific portion or range of the day during which an activity, service, or condition is in effect or applicable.
-
B.
hasTimeOfDay
chosen
Indicates that a situation, event, or state occurs during, or is associated with, a specific part of the day (e.g., morning, afternoon, evening, night).
-
C.
dayPattern
Indicates the recurring schedule or configuration of days on which an event, action, or condition occurs.
-
D.
landingTimeOfDay
Indicates the time of day at which a landing event occurs.
-
E.
timeStatus
Indicates the temporal state or condition of an event or entity relative to a reference time (e.g., past, present, future, ongoing, or scheduled).
- 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_69d6aae4dfa48190a3ab0b19a159a3c5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d886e3ad548190b2c88332f5d919bd |
completed | April 10, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69d8087cbe7c819085680f3d67ccc978 |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:37 p.m.