Triple
T36793625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gunhilda of Denmark |
E909119
|
entity |
| Predicate | notableTitleContext |
P154324
|
FINISHED |
| Object | one of the earliest Danish-born Holy Roman empresses |
—
|
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: one of the earliest Danish-born Holy Roman empresses | Statement: [Gunhilda of Denmark, notableTitleContext, one of the earliest Danish-born Holy Roman empresses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableTitleContext Context triple: [Gunhilda of Denmark, notableTitleContext, one of the earliest Danish-born Holy Roman empresses]
-
A.
notableTitleType
Indicates that a title associated with an entity is of a type considered notable or especially significant.
-
B.
notableTitleOnTheLine
Indicates that a significant or prestigious title is at stake or being contested in the associated event or context.
-
C.
notableTitleAssociation
chosen
Indicates an association where an entity is linked to a distinguished or noteworthy title, role, or honor it holds or has held.
-
D.
notableTitleOrigin
Indicates that a notable or distinguished title held by an entity originates from, or is derived from, a specified source or context.
-
E.
titleContext
Indicates the contextual information or surrounding circumstances in which a title is used, interpreted, or assigned.
- 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_69f76e7b98888190899b6478a82ad6ae |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0e039481908a4a2666f76c5363 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:12 p.m.