Triple
T24972140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Le Petit Dauphin |
E624918
|
entity |
| Predicate | hasReferentGrandfather |
P61441
|
FINISHED |
| Object | Louis XIV of France |
—
|
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: Louis XIV of France | Statement: [Le Petit Dauphin, hasReferentGrandfather, Louis XIV of France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReferentGrandfather Context triple: [Le Petit Dauphin, hasReferentGrandfather, Louis XIV of France]
-
A.
hasReferentFather
Indicates that an entity’s referent is the father of another entity.
-
B.
possibleGrandfatherOf
Indicates that one individual may be the grandfather of another, typically as the father of one of the other person’s parents, but with some uncertainty or lack of confirmation.
-
C.
grandfatherIs
chosen
Indicates that one entity is the grandfather (parent of a parent) of another entity.
-
D.
hasPaternalGrandparent
Indicates that one entity is the paternal grandparent (father’s parent) of another entity.
-
E.
hasGrandchildOfPatriarch
Indicates that one entity is a grandchild of a specified patriarch in a family or lineage relationship.
- 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_69e2ff24512481908e9a72315b8d0354 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 18, 2026, 6:01 a.m.