Triple
T30247793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess of Réthy |
E769104
|
entity |
| Predicate | monarchAtTimeOfGrant |
P33027
|
FINISHED |
| Object | Leopold III of Belgium |
—
|
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: Leopold III of Belgium | Statement: [Princess of Réthy, monarchAtTimeOfGrant, Leopold III of Belgium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: monarchAtTimeOfGrant Context triple: [Princess of Réthy, monarchAtTimeOfGrant, Leopold III of Belgium]
-
A.
monarchWhoGrantedTitle
chosen
Indicates the monarch who conferred or bestowed a particular title upon an individual.
-
B.
currentHolderMonarchAtGrant
Indicates that the monarch who currently holds a title or position is the same monarch who held it at the time the title or privilege was originally granted.
-
C.
monarchAtTime
Indicates that a specified person holds the position of monarch of a given polity during a particular time or time interval.
-
D.
monarchWhoGrants
Indicates a relationship where a monarch bestows, confers, or grants something (such as rights, titles, lands, or privileges) to another party.
-
E.
monarchyEstablished
Indicates that a monarchical form of government has been formally created or instituted for a given entity or territory.
- 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_69f224831dc08190b2e569b987264057 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6a916d2e08190bafc01cba73b6469 |
completed | May 3, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 29, 2026, 7:39 p.m.