Triple
T317900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ethiopia |
E7746
|
entity |
| Predicate | usesClockSystem |
P12924
|
FINISHED |
| Object | 12-hour day clock starting at sunrise |
—
|
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: 12-hour day clock starting at sunrise | Statement: [Ethiopia, usesClockSystem, 12-hour day clock starting at sunrise]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesClockSystem Context triple: [Ethiopia, usesClockSystem, 12-hour day clock starting at sunrise]
-
A.
hasClock
Indicates that one entity possesses, contains, or is equipped with a clock.
-
B.
hasClockTower
Indicates that one entity possesses or features a clock tower as part of its structure or property.
-
C.
isStandardTimeFor
Indicates that a specified time zone or region is currently observing its standard (non-daylight-saving) time.
-
D.
observesSameTimeAs
Indicates that two observation events occur simultaneously or during the same time interval.
-
E.
standardTimeCounterpart
Indicates that one time representation is the corresponding value expressed in a standard or canonical time format for the other.
- F. None of above. chosen
Provenance (4 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_69a2e7e7af7881908890039d6be4e9b8 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eb7df63c8190b7cd1bcfdfd96187 |
completed | Feb. 28, 2026, 1:19 p.m. |
| PD | Predicate disambiguation | batch_69a2e94513ec819089f5177f7a521e65 |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2eb7c56bc8190ab787801af2eec8d |
completed | Feb. 28, 2026, 1:19 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.