Triple
T10511352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baron Kelvin |
E247921
|
entity |
| Predicate | fieldAssociatedWithTitleHolder |
P94302
|
FINISHED |
| Object | physics |
—
|
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: physics | Statement: [Baron Kelvin, fieldAssociatedWithTitleHolder, physics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fieldAssociatedWithTitleHolder Context triple: [Baron Kelvin, fieldAssociatedWithTitleHolder, physics]
-
A.
associatedWithTitleHolderRole
Indicates a relationship where an entity is connected to, or linked with, a role held by a title holder.
-
B.
refersToTitleHolder
Indicates that one entity makes reference to, or designates, the entity that currently holds a specific title or position.
-
C.
relatedTitleHolder
Indicates that one entity holds a title or position that is related or connected to the title or position held by another entity.
-
D.
hasTitleHolderFamilyRelation
Indicates a family relationship between the current title holder and another person, specifying how they are related within the title holder’s family.
-
E.
titleHolderField
Indicates that one entity serves as the designated holder or owner of a specific title associated with another entity.
- F. None of above. chosen
Provenance (4 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_69d381c4aa948190942e1d803143fb0e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509b5fcb8819087a23a2b26aecd70 |
completed | April 7, 2026, 1:42 p.m. |
| PD | Predicate disambiguation | batch_69d4fb919ea08190bcc1193e2014d437 |
completed | April 7, 2026, 12:41 p.m. |
| PDg | Predicate description generation | batch_69d4fe058fcc81909428137d9ffd6d90 |
completed | April 7, 2026, 12:52 p.m. |
Created at: April 6, 2026, 12:27 p.m.