Triple
T29578936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French legitimism |
E753519
|
entity |
| Predicate | sawAsHeir |
P167461
|
FINISHED |
| Object | Bourbon pretender to the French throne |
—
|
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: Bourbon pretender to the French throne | Statement: [French legitimism, sawAsHeir, Bourbon pretender to the French throne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sawAsHeir Context triple: [French legitimism, sawAsHeir, Bourbon pretender to the French throne]
-
A.
succeededAsHeir
Indicates that one entity became the heir in place of, or following, another entity, typically upon the latter’s death or abdication.
-
B.
agreedHeir
Indicates that one entity has been formally designated and accepted as the heir of another, typically through mutual agreement or legal arrangement.
-
C.
adoptedAsHeir
Indicates that one entity has been formally chosen and accepted as the legal heir or successor of another entity.
-
D.
madeHeirBy
Indicates that one entity is designated or appointed as the heir of another entity.
-
E.
usedByHeir
Indicates that something is utilized or employed by an heir.
- F. None of above. chosen
Provenance (4 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_69f0ef80bf8c8190ad286e99f7df0c63 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f66d7825c08190953242afe9572940 |
completed | May 2, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
| PDg | Predicate description generation | batch_69f6691da93081909deaf680614fc900 |
completed | May 2, 2026, 9:14 p.m. |
Created at: April 28, 2026, 6:05 p.m.