Triple
T17804699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ed Kelce |
E444524
|
entity |
| Predicate | parentOfPosition |
P128985
|
FINISHED |
| Object | father of an NFL tight end |
—
|
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: father of an NFL tight end | Statement: [Ed Kelce, parentOfPosition, father of an NFL tight end]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parentOfPosition Context triple: [Ed Kelce, parentOfPosition, father of an NFL tight end]
-
A.
parentPosition
Indicates that one entity occupies the role of a parent or higher-level position relative to another entity in a hierarchical structure.
-
B.
positionHeldByParent
Indicates that a position or role is held by the parent of the referenced entity.
-
C.
parentFrom
Indicates that one entity is the parent (biological, adoptive, or legal) of another entity.
-
D.
isParentOf
Indicates that one entity is the biological or legal parent of another entity.
-
E.
fatherPosition
Indicates the spatial or positional relationship occupied by a father relative to another referenced entity or location.
- 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_69d8b9efe370819095cd219b143ae727 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48802bcfc8190a138164d11081ab8 |
completed | April 19, 2026, 7:45 a.m. |
| PD | Predicate disambiguation | batch_69e3d8de28688190844b65acf6af54e6 |
completed | April 18, 2026, 7:17 p.m. |
| PDg | Predicate description generation | batch_69e3db7704588190a34a422421152173 |
completed | April 18, 2026, 7:28 p.m. |
Created at: April 10, 2026, 10:14 a.m.