Triple
T33873679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bad Blake |
E868292
|
entity |
| Predicate | hasPastRelationshipWith |
P64436
|
FINISHED |
| Object | Tommy Sweet |
—
|
NE NERFINISHED |
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: Tommy Sweet | Statement: [Bad Blake, hasPastRelationshipWith, Tommy Sweet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPastRelationshipWith Context triple: [Bad Blake, hasPastRelationshipWith, Tommy Sweet]
-
A.
wasInRelationshipDuring
Indicates that two entities were in a romantic or otherwise defined interpersonal relationship with each other during a specified time period.
-
B.
hasBeenDatedBy
chosen
Indicates that one entity has previously been in a romantic or dating relationship with another entity.
-
C.
hadPartner
Indicates that an entity was in a romantic or life-partner relationship with another entity at some point in time.
-
D.
formerRelationshipStatus
Indicates that a relationship between entities existed in the past but no longer holds in the present.
-
E.
haveRelationshipWith
Indicates that one entity is in some form of defined relationship or association with another entity.
- 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_69f34995029081909ede0f7df73d1a5e |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff63225b6481909217ad11b4f7d3ba |
completed | May 9, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ff60e0882c819085d097010db43ee0 |
completed | May 9, 2026, 4:29 p.m. |
Created at: May 1, 2026, 1:47 a.m.