Triple
T38470535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince of Orléans |
E912702
|
entity |
| Predicate | linkedHouseFounder |
P139217
|
FINISHED |
| Object | Philippe I, Duke of Orléans |
—
|
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: Philippe I, Duke of Orléans | Statement: [Prince of Orléans, linkedHouseFounder, Philippe I, Duke of Orléans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedHouseFounder Context triple: [Prince of Orléans, linkedHouseFounder, Philippe I, Duke of Orléans]
-
A.
belongsToHouseFounder
chosen
Indicates that an entity is the original creator or establisher of a particular house or lineage.
-
B.
linkedInstitutionFounder
Indicates that an entity is the founder or co-founder of an institution with which another entity is associated or linked.
-
C.
founderAlsoOwns
Indicates that the person or entity who founded something also retains ownership of it.
-
D.
founderRelation
Indicates that one entity is the founder or creator of another entity, such as an organization, project, or initiative.
-
E.
sharesFounderWith
Indicates that two entities have at least one founder in common.
- 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_69f76e861d8c81908559031dc66e3c15 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff1e3e13c08190bb8990c44716b746 |
completed | May 9, 2026, 11:45 a.m. |
| PD | Predicate disambiguation | batch_69ff1dfcaf2c8190aaf2b428d57b7782 |
completed | May 9, 2026, 11:43 a.m. |
Created at: May 3, 2026, 4:31 p.m.