Triple
T14384377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mercédès |
E356684
|
entity |
| Predicate | relationshipWithAlbertDeMorcerf |
P114026
|
FINISHED |
| Object | devoted mother |
—
|
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: devoted mother | Statement: [Mercédès, relationshipWithAlbertDeMorcerf, devoted mother]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipWithAlbertDeMorcerf Context triple: [Mercédès, relationshipWithAlbertDeMorcerf, devoted mother]
-
A.
relationshipToMadameMerle
Indicates the specific nature or type of relationship an entity has with Madame Merle.
-
B.
relationshipToBaudelaires
Indicates the type of personal or familial connection an entity has to the Baudelaires.
-
C.
relationshipToBaron de Wolmar
Indicates the nature or type of connection, association, or role that one entity has in relation to Baron de Wolmar.
-
D.
relationshipTypeWithRobertAngier
Indicates the specific nature or category of relationship that an entity has with Robert Angier.
-
E.
relationshipToMorganAlexander
Indicates the specific type of relationship or connection an entity has to Morgan Alexander.
- 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_69d827927c988190ad98bb0360981783 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de9025cff881908c08224d90d9f750 |
completed | April 14, 2026, 7:06 p.m. |
| PD | Predicate disambiguation | batch_69de2aa024c48190805df6a9d63deb10 |
completed | April 14, 2026, 11:53 a.m. |
| PDg | Predicate description generation | batch_69de2e08b6c08190bb4c929deab236a6 |
completed | April 14, 2026, 12:07 p.m. |
Created at: April 10, 2026, 1:16 a.m.