Triple
T25942919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Henry of Battenberg |
E653755
|
entity |
| Predicate | holderRoyalHouse |
P8992
|
FINISHED |
| Object | House of Windsor |
—
|
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: House of Windsor | Statement: [Princess Henry of Battenberg, holderRoyalHouse, House of Windsor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holderRoyalHouse Context triple: [Princess Henry of Battenberg, holderRoyalHouse, House of Windsor]
-
A.
relatedRoyalHouse
Indicates a relationship where one royal house is historically, genealogically, or politically connected to another royal house.
-
B.
reigningRoyalHouseOf
Indicates that a particular royal house currently holds the ruling monarchy over a specified realm or country.
-
C.
notableRoyalHouse
Indicates that an entity is prominently associated with, or belongs to, a particular royal house or dynasty.
-
D.
hasRoyalHouse
chosen
Indicates that an entity is associated with or belongs to a particular royal house or dynasty.
-
E.
crownedMonarchHouse
Indicates that a particular royal house is the one from which a given monarch was crowned or to which that crowned monarch belongs.
- 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_69e7ab3fd2f881908837305e4ba98011 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6046115b88190aa9011f53a54cddc |
completed | May 2, 2026, 2:04 p.m. |
| PD | Predicate disambiguation | batch_69f5afec3e94819080d9ba86cf8c866e |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 22, 2026, 8:41 a.m.