Triple
T35970221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoff Mercer |
E1040260
|
entity |
| Predicate | hasPastRomanticRelationshipWith |
P64436
|
FINISHED |
| Object | Katya |
—
|
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: Katya | Statement: [Geoff Mercer, hasPastRomanticRelationshipWith, Katya]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPastRomanticRelationshipWith Context triple: [Geoff Mercer, hasPastRomanticRelationshipWith, Katya]
-
A.
hasRomanticEncounterWith
Indicates that two entities engage in or share a romantic or intimate encounter with each other.
-
B.
wasInRelationshipDuring
Indicates that two entities were in a romantic or otherwise defined interpersonal relationship with each other during a specified time period.
-
C.
hadPartner
Indicates that an entity was in a romantic or life-partner relationship with another entity at some point in time.
-
D.
romanticOrSexualPartners
Indicates that the entities have been, are, or are intended to be involved as romantic and/or sexual partners with each other.
-
E.
hasBeenDatedBy
chosen
Indicates that one entity has previously been in a romantic or dating relationship 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_69f76e27758c81909b711cf38a130aaf |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ffecdcbac4819093b725a7dbe0e61b |
completed | May 10, 2026, 2:26 a.m. |
| PD | Predicate disambiguation | batch_69ffec3633288190adbbd84e277708dc |
completed | May 10, 2026, 2:23 a.m. |
Created at: May 3, 2026, 4:07 p.m.