Triple
T35975116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Balfour |
E1040389
|
entity |
| Predicate | relationshipToEbenezerBalfour |
P207120
|
FINISHED |
| Object | nephew |
—
|
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: nephew | Statement: [David Balfour, relationshipToEbenezerBalfour, nephew]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToEbenezerBalfour Context triple: [David Balfour, relationshipToEbenezerBalfour, nephew]
-
A.
relationshipToBartholomew
Indicates the specific type of relationship or connection an entity has to the individual named Bartholomew.
-
B.
relationshipToElijahBaley
Indicates the nature or type of relationship an entity has with Elijah Baley.
-
C.
relationshipToEliDavid
Indicates the specific familial, professional, or personal relationship that an entity has with Eli David.
-
D.
relationshipToAlBundy
Indicates the specific familial, social, or personal relationship that an entity has to the person Al Bundy.
-
E.
relationshipWithBritish
Indicates that there exists some form of connection, association, or involvement between an entity and Britain or British people, institutions, or culture.
- 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_69f76e27758c81909b711cf38a130aaf |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0895b48190acdd88dc10db7be7 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c82179081908325a59b8539b3a8 |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:07 p.m.