Triple
T29178842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ernesto de la Cruz (Coco character) |
E739691
|
entity |
| Predicate | relationshipToHéctor |
P202986
|
FINISHED |
| Object | former friend |
—
|
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: former friend | Statement: [Ernesto de la Cruz (Coco character), relationshipToHéctor, former friend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToHéctor Context triple: [Ernesto de la Cruz (Coco character), relationshipToHéctor, former friend]
-
A.
relationshipToMiguel
Indicates the nature or type of relationship that one entity has with Miguel.
-
B.
relationToHernanReyes
Indicates a specified type of relationship or connection that an entity has to Hernan Reyes.
-
C.
relationshipToCarmen
Indicates the specific type of personal or social relationship an entity has with Carmen.
-
D.
relationshipTypeWith Aureliano Segundo
Indicates the specific nature or category of relational connection that an entity has with Aureliano Segundo.
-
E.
relationshipToHeracles
Indicates the specific familial or social relationship that an entity has to Heracles.
- 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_69f07cb74c2c8190ad396487fcb4fde6 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_6a00d8ba18808190976682088a02a9a8 |
completed | May 10, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_6a00d85fad64819084f424ec8ecd3b57 |
completed | May 10, 2026, 7:11 p.m. |
| PDg | Predicate description generation | batch_6a00d8b8eac08190809c78998e09c47c |
completed | May 10, 2026, 7:12 p.m. |
Created at: April 28, 2026, 11:56 a.m.