Triple
T23396215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie Zéphyrine of France |
E559365
|
entity |
| Predicate | statusAtBirth |
P34200
|
FINISHED |
| Object | legitimate child of the Dauphin of France |
—
|
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: legitimate child of the Dauphin of France | Statement: [Marie Zéphyrine of France, statusAtBirth, legitimate child of the Dauphin of France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statusAtBirth Context triple: [Marie Zéphyrine of France, statusAtBirth, legitimate child of the Dauphin of France]
-
A.
birthStatus
chosen
Indicates the condition or circumstances of an entity’s birth, such as whether and how it was born.
-
B.
birthStatusInSeries
Indicates the status or circumstances of an entity’s birth as depicted within a particular series or narrative.
-
C.
birthWeight
Indicates the recorded weight of an individual at the time of their birth.
-
D.
birthType
Indicates the manner or method by which a birth occurred or was brought about.
-
E.
freeStatusAtBirth
Indicates whether an individual was legally considered free or enslaved at the moment of their birth.
- 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_69e24549610c8190a069d6411ce5f661 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a4dc48008190bdcf92f8d9a5232d |
completed | April 29, 2026, 6:27 a.m. |
| PD | Predicate disambiguation | batch_69f061dde2e481908308952f9c0d3c2e |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:36 p.m.