Triple
T30766114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arms of the Duke of Hamilton |
E783375
|
entity |
| Predicate | crestBelongsTo |
P39797
|
FINISHED |
| Object | Duke of Hamilton |
—
|
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: Duke of Hamilton | Statement: [Arms of the Duke of Hamilton, crestBelongsTo, Duke of Hamilton]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crestBelongsTo Context triple: [Arms of the Duke of Hamilton, crestBelongsTo, Duke of Hamilton]
-
A.
crest
Indicates reaching the highest point or peak of something, such as a wave, hill, or trend, before it begins to decline.
-
B.
crestFeature
Indicates that an entity possesses a notable crest-related characteristic or structural feature.
-
C.
crestType
Indicates the specific style or form of a crest associated with an entity.
-
D.
crestElement
chosen
Indicates that one entity is a crest or emblematic design element associated with, or forming part of, another entity.
-
E.
crestMaterial
Indicates that one entity is the material from which another entity’s crest is made.
- 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_69f224b047f48190b4f5efeb7ee97b37 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f68fbe1b2881909ca26a21f9e67ddc |
completed | May 2, 2026, 11:58 p.m. |
| PD | Predicate disambiguation | batch_69f686140aa08190a35f62572b2db9b6 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:40 p.m.