Triple
T36043198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ali (Ali & Ava) |
E1042597
|
entity |
| Predicate | relationshipTypeWith Ava (Ali & Ava) |
P207144
|
FINISHED |
| Object | unexpected romance |
—
|
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: unexpected romance | Statement: [Ali (Ali & Ava), relationshipTypeWith Ava (Ali & Ava), unexpected romance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWith Ava (Ali & Ava) Context triple: [Ali (Ali & Ava), relationshipTypeWith Ava (Ali & Ava), unexpected romance]
-
A.
relationshipToAli
Indicates the specific type of relationship or connection that one entity has to Ali.
-
B.
relationshipToEva
Indicates a specified type of personal or social relationship that an entity has with Eva.
-
C.
relationshipToAlice
Indicates the specific type of relationship or connection that an entity has with Alice.
-
D.
inRelationshipWith
Indicates that two entities are mutually involved in a defined personal, romantic, or partnership relationship with each other.
-
E.
haveRelationshipWith
Indicates that one entity is in some form of defined relationship or association with another entity.
- 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_69f76e2d7e8c8190bac4e90734566799 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0895b48190acdd88dc10db7be7 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c82179081908325a59b8539b3a8 |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:07 p.m.