Triple
T31730274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romania (Byzantine Italy) |
E809840
|
entity |
| Predicate | gradualLossTo |
P172473
|
FINISHED |
| Object | Lombard principalities |
—
|
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: Lombard principalities | Statement: [Romania (Byzantine Italy), gradualLossTo, Lombard principalities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gradualLossTo Context triple: [Romania (Byzantine Italy), gradualLossTo, Lombard principalities]
-
A.
causedLossOf
Indicates that one entity brought about or was responsible for another entity experiencing a loss.
-
B.
graduallyPhasedOutIn
Indicates that something is discontinued or removed in a particular context or period through a slow, step-by-step process rather than all at once.
-
C.
gradualProcess
Indicates a process or change that occurs slowly over time through small, incremental steps rather than abruptly.
-
D.
graduallyEmbraces
Indicates a relationship in which one entity slowly and progressively accepts, adopts, or takes in another entity or its influence over time.
-
E.
declineIn
Indicates a relationship where one entity experiences a decrease or reduction in the level, amount, or intensity of another entity over time.
- 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_69f348e0e4908190a884582eca646fb7 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6abe15d5c81909ccf4ce37f78bc43 |
completed | May 3, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
| PDg | Predicate description generation | batch_69f6aaf31a548190b2f792ff4b8c002a |
completed | May 3, 2026, 1:54 a.m. |
Created at: April 30, 2026, 11:21 p.m.