Triple
T35564492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prime Minister of the Kingdom of Serbs, Croats and Slovenes |
E1027729
|
entity |
| Predicate | termStartOfState |
P16146
|
FINISHED |
| Object | 1918-12-01 |
—
|
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: 1918-12-01 | Statement: [Prime Minister of the Kingdom of Serbs, Croats and Slovenes, termStartOfState, 1918-12-01]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: termStartOfState Context triple: [Prime Minister of the Kingdom of Serbs, Croats and Slovenes, termStartOfState, 1918-12-01]
-
A.
termStartOfSecondHolder
Indicates that the term or tenure being referred to marks the beginning of the second holder’s period in that role or relationship.
-
B.
startPointState
Indicates the initial state or condition from which a process, event, or transition begins.
-
C.
firstTermStart
Indicates that an entity marks the starting point or initial term in an ordered sequence, period, or agreement.
-
D.
termStartOfWinner
Indicates the starting date or point in time of the winner’s term in a given role or position.
-
E.
statePowerStartDate
chosen
Indicates the date on which a state or governing authority first began to exercise its official power or jurisdiction.
- 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_69f76e020fd8819081cb080e7e203083 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79a54aa3c8190b2bb5d790b2d42d4 |
completed | May 3, 2026, 6:56 p.m. |
| PD | Predicate disambiguation | batch_69f7961970408190b669cc556e30a608 |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:04 p.m.