Triple
T9435349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Elizabeth, Duchess of Edinburgh |
E227490
|
entity |
| Predicate | holderStartDate |
P288
|
FINISHED |
| Object | 1947-11-20 |
—
|
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: 1947-11-20 | Statement: [Princess Elizabeth, Duchess of Edinburgh, holderStartDate, 1947-11-20]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holderStartDate Context triple: [Princess Elizabeth, Duchess of Edinburgh, holderStartDate, 1947-11-20]
-
A.
previousHolderStartDate
Indicates the date on which the immediately preceding holder of something (e.g., a position, title, or asset) began their tenure or ownership.
-
B.
holdingDate
Indicates the date on which a holding, possession, or ownership of something is recorded or takes effect.
-
C.
effectivePeriodStart
Indicates the date and time when a specified condition, status, or agreement becomes valid or goes into effect.
-
D.
partnerStartDate
Indicates the date on which the partnership or partner relationship between the entities begins.
-
E.
startDate
chosen
Indicates the point in time when an event, state, or relationship begins.
- 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_69ca8437a7ac81908651de48f2d2141d |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd7e64109081908222f590928bc572 |
completed | April 1, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69cca55548488190b171ae695a3212de |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:50 p.m.