Triple
T26375073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prins van Waterloo |
E660875
|
entity |
| Predicate | holderStart |
P7037
|
FINISHED |
| Object | Arthur Wellesley, 1st Duke of Wellington |
—
|
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: Arthur Wellesley, 1st Duke of Wellington | Statement: [Prins van Waterloo, holderStart, Arthur Wellesley, 1st Duke of Wellington]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holderStart Context triple: [Prins van Waterloo, holderStart, Arthur Wellesley, 1st Duke of Wellington]
-
A.
holderIs
Indicates that one entity serves as the holder, possessor, or container of another entity.
-
B.
currentHolderStart
chosen
Indicates the point in time when an entity’s current holder or possessor first began holding it.
-
C.
holderField
Indicates that a specified field or attribute belongs to, is maintained by, or is associated with a particular holder entity.
-
D.
holderMayBe
Indicates that a particular entity is allowed or permitted to serve as the holder or possessor of another entity.
-
E.
holder
Indicates that one entity possesses, controls, or has custody of another entity, typically in a temporary or contextual sense.
- 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_69ee812a698881908d6a58265995fa39 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f6106f23cc8190854556a454648ab0 |
completed | May 2, 2026, 2:55 p.m. |
| PD | Predicate disambiguation | batch_69f60b89cc048190a9feb24466006be0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 26, 2026, 11 p.m.