Triple
T11806753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Balfour |
E280765
|
entity |
| Predicate | relationshipToVictims |
P101216
|
FINISHED |
| Object | estranged husband of Julia Hudson |
—
|
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: estranged husband of Julia Hudson | Statement: [William Balfour, relationshipToVictims, estranged husband of Julia Hudson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToVictims Context triple: [William Balfour, relationshipToVictims, estranged husband of Julia Hudson]
-
A.
victimRelation
Indicates that one entity is the victim or target of harm, wrongdoing, or an adverse action caused by another entity.
-
B.
hasRelationshipToPerpetrator
chosen
Indicates that an entity has a specified type of relationship or connection to the perpetrator of an act or event.
-
C.
victimGroupHelped
Indicates that assistance, support, or aid was provided to a group identified as victims.
-
D.
victimGroup
Indicates that one group or entity is the target or recipient of harm, abuse, or wrongdoing caused by another.
-
E.
isVictimOf
Indicates that one entity suffers harm, loss, or wrongdoing as a result of another entity’s actions or events.
- 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_69d6ab26aae88190b2489efcb2a24234 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a658f918819092c2db05fe2ab0ce |
completed | April 10, 2026, 7:27 a.m. |
| PD | Predicate disambiguation | batch_69d8a24e9a088190aff7932d1ff93dbf |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:42 p.m.