Triple
T23988515
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of the French Empire |
E605001
|
entity |
| Predicate | nobleRankInFrench |
P66828
|
FINISHED |
| Object | duc |
—
|
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: duc | Statement: [Duke of the French Empire, nobleRankInFrench, duc]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nobleRankInFrench Context triple: [Duke of the French Empire, nobleRankInFrench, duc]
-
A.
rankInFrenchPeerage
Indicates the hierarchical noble rank an entity holds within the French system of peerage.
-
B.
nobleRankIn
chosen
Indicates that an entity holds a specified noble rank within a particular political or territorial jurisdiction.
-
C.
nobleRankInOrder
Indicates that an entity holds a specific noble rank at a particular position within an established order of nobility.
-
D.
nobleRankInHierarchy
Indicates the relative position or level of a noble title within a structured hierarchy of ranks.
-
E.
nobleRankAbove
Indicates that one entity holds a higher noble rank or title in a hierarchy than 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_69e295463f7c8190b1c19dbd114641b9 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d38902fc8190af51cedfce1c6c13 |
completed | April 29, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69f1615994c48190a5de95d3f7e5cd0a |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:37 p.m.