Triple
T32098498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Count Palatine of Cephalonia and Zakynthos |
E819781
|
entity |
| Predicate | territorySometimesIncluded |
P29773
|
FINISHED |
| Object | Lefkada |
—
|
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: Lefkada | Statement: [Count Palatine of Cephalonia and Zakynthos, territorySometimesIncluded, Lefkada]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: territorySometimesIncluded Context triple: [Count Palatine of Cephalonia and Zakynthos, territorySometimesIncluded, Lefkada]
-
A.
territoryIncluded
Indicates that one territory is geographically or administratively contained within another territory.
-
B.
sometimesIncludesTerritory
chosen
Indicates that one entity occasionally, but not consistently, encompasses or contains the territory of another entity.
-
C.
territoryOriginallyIncluded
Indicates that an earlier or original territorial boundary encompassed the referenced area or entity.
-
D.
includedTerritoryType
Indicates that one territory type is contained within, or forms part of, another territory type.
-
E.
territoryCorrespondedTo
Indicates that one territory matched, aligned with, or was equivalent to another territory in scope, boundaries, or designation.
- 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_69f34901106881908ea893ad504a08be |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f70e8755a48190931eaa77946f9460 |
completed | May 3, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f70abc00848190a1c3f495ef6c8dc6 |
completed | May 3, 2026, 8:43 a.m. |
Created at: May 1, 2026, 12:26 a.m.