Triple
T15622565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anse Bundren |
E375592
|
entity |
| Predicate | hasChildRelationType |
P109081
|
FINISHED |
| Object | often neglectful father |
—
|
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: often neglectful father | Statement: [Anse Bundren, hasChildRelationType, often neglectful father]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasChildRelationType Context triple: [Anse Bundren, hasChildRelationType, often neglectful father]
-
A.
hasRelation
Indicates that there exists some specified relationship or association between two entities.
-
B.
hasSymbolicRelationshipType
Indicates that there exists a symbolic (non-literal) relationship of a specified type between two entities.
-
C.
hasCentralRelationshipType
Indicates that there exists a primary or most significant type of relationship that characterizes how two entities are related to each other.
-
D.
hasSubcategoryRelation
Indicates that one category is a more specific subdivision or subset of another broader category.
-
E.
hasParentChildDynamicWith
chosen
Indicates a relationship in which one entity assumes a parental role and the other assumes a child role, involving hierarchical care, guidance, or authority dynamics between them.
- 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_69d85ccf2794819096cda4cbcb02d478 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e9a95f08190b0013ba1428849d3 |
completed | April 16, 2026, 2:51 a.m. |
| PD | Predicate disambiguation | batch_69deda868d4481908f4bce1c64d2902a |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:14 a.m.