Triple
T29190862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Leroy |
E739984
|
entity |
| Predicate | relationshipToNina |
P203028
|
FINISHED |
| Object | mentor |
—
|
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: mentor | Statement: [Thomas Leroy, relationshipToNina, mentor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToNina Context triple: [Thomas Leroy, relationshipToNina, mentor]
-
A.
relationshipToTina
Indicates the specific type of personal or social relationship that an entity has with Tina.
-
B.
relationshipToNicole
Indicates the specific type of relationship or connection that an entity has with Nicole.
-
C.
relationshipToTinaBordereau
Indicates the specific type of personal or professional relationship an entity has with Tina Bordereau.
-
D.
relationshipToPolinaAlexandrovna
Indicates the specific type of personal or social relationship that one entity has with Polina Alexandrovna.
-
E.
relationshipToNicholas
Indicates the specific familial, social, or professional relationship that one entity has to Nicholas.
- 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_69f07cb8033c8190b8807e219a14333d |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_6a0116ca6a1c81909a9e938dbe54eb8a |
completed | May 10, 2026, 11:37 p.m. |
| PD | Predicate disambiguation | batch_6a0116655e248190bdfe5b4bb4f1cf47 |
completed | May 10, 2026, 11:36 p.m. |
| PDg | Predicate description generation | batch_6a0116c9a0ac8190ae77f1c4ccd461ba |
completed | May 10, 2026, 11:37 p.m. |
Created at: April 28, 2026, 12:02 p.m.