Triple
T27321019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sibylla of Flanders |
E689494
|
entity |
| Predicate | regionRuledAsQueenConsort |
P59097
|
FINISHED |
| Object | Jerusalem |
—
|
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: Jerusalem | Statement: [Sibylla of Flanders, regionRuledAsQueenConsort, Jerusalem]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionRuledAsQueenConsort Context triple: [Sibylla of Flanders, regionRuledAsQueenConsort, Jerusalem]
-
A.
reignAsQueenConsort
chosen
Indicates that a person holds the position and performs the role of queen consort during the reign of a monarch.
-
B.
reignAsQueenConsortFrom
Indicates the time period during which a person held the role of queen consort, starting from a specified date or event.
-
C.
producedQueenConsort
Indicates that one entity gave rise to or is the origin of another entity who became a queen consort.
-
D.
typeOfMonarchConsort
Indicates the specific kind or category of monarch’s spouse (consort) that an entity is, such as queen consort, prince consort, or empress consort.
-
E.
regentSpouse
Indicates that one person is the spouse of a regent, i.e., married to an individual who rules on behalf of a monarch or in place of the sovereign.
- 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_69ef355c53a08190a8a92e355a7ce115 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f7b0e5744c8190a22c1e1d6fcfa466 |
completed | May 3, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f7ab70d034819080295628497d8582 |
completed | May 3, 2026, 8:09 p.m. |
Created at: April 27, 2026, 11:33 a.m.