Triple
T30147858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iraqi Republic Day |
E766304
|
entity |
| Predicate | startEventCountryAtTime |
P86963
|
FINISHED |
| Object | Hashemite Kingdom of Iraq |
—
|
NE NERFINISHED |
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: Hashemite Kingdom of Iraq | Statement: [Iraqi Republic Day, startEventCountryAtTime, Hashemite Kingdom of Iraq]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startEventCountryAtTime Context triple: [Iraqi Republic Day, startEventCountryAtTime, Hashemite Kingdom of Iraq]
-
A.
introducedForEventInCountry
Indicates that something was introduced specifically for an event that took place in a particular country.
-
B.
startsInCountry
Indicates that an entity’s starting point or origin location is situated within a specified country.
-
C.
locatedInCountryDuringEvent
chosen
Indicates that an entity was situated within a specific country for the duration or at the time of a particular event.
-
D.
countryOfFirstEvent
Indicates the country in which the first event in a sequence or series took place.
-
E.
refersToEventCountry
Indicates that one entity references or is associated with the country in which a particular event takes place.
- 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_69f2247909048190ae86c2160cf8b566 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69feafa1ba0081909013800b85a9f613 |
completed | May 9, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69feae58d62c81909d031f3df8992883 |
completed | May 9, 2026, 3:47 a.m. |
Created at: April 29, 2026, 7:19 p.m.