Triple
T24768994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Transylvania Company |
E619667
|
entity |
| Predicate | proposedColonyName |
P122252
|
FINISHED |
| Object | Transylvania |
—
|
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: Transylvania | Statement: [Transylvania Company, proposedColonyName, Transylvania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: proposedColonyName Context triple: [Transylvania Company, proposedColonyName, Transylvania]
-
A.
proposedColony
chosen
Indicates that an entity has been suggested or put forward as a potential colony, but has not yet been established or confirmed as one.
-
B.
colonyName
Indicates that a colony entity is associated with and identified by a specific name.
-
C.
proposedStateName
Indicates that one entity has suggested or put forward a particular name to be used as the state name for another entity.
-
D.
colonyOf
Indicates that one entity is a colony belonging to, founded by, or politically dependent on another entity.
-
E.
nameProposedBy
Indicates that one entity is the proposer or originator of a particular name assigned to another entity.
- 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_69e2fabd04488190a2d13c97be745a2d |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f410a8dc8081909e2f4b65485a6786 |
completed | May 1, 2026, 2:32 a.m. |
| PD | Predicate disambiguation | batch_69f40ef612c88190ab2f3f08d4a92018 |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 4:29 a.m.