Triple
T34268529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baron of Rosny |
E879240
|
entity |
| Predicate | notableHolderTitleEvolution |
P93235
|
FINISHED |
| Object | later Duke of Sully |
—
|
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: later Duke of Sully | Statement: [Baron of Rosny, notableHolderTitleEvolution, later Duke of Sully]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableHolderTitleEvolution Context triple: [Baron of Rosny, notableHolderTitleEvolution, later Duke of Sully]
-
A.
hasNotableTitleHolderWhoBecame
chosen
Indicates that an entity has a notable title holder who later attained or transitioned into another specified role, status, or position.
-
B.
titleHolderNotably
Indicates that an entity holds a particular title in a way that is especially notable, distinguished, or worthy of specific mention.
-
C.
historicalTitleChange
Indicates that an entity’s official title has changed at some point in history, linking the old title to the new one.
-
D.
notableTitleHeld
Indicates that an entity has held a distinguished or noteworthy title, rank, or official position.
-
E.
titleHolderServedAs
Indicates that the entity holding a particular title also performed the role or function associated with that title.
- 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_69f349b4f5fc819094b441d18e95e5f1 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379fbe4a08190bfe65ebd141164e9 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:56 a.m.