Triple
T27617607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harold Mitch Mitchell |
E700480
|
entity |
| Predicate | relationshipStatusWithBlanche |
P150354
|
FINISHED |
| Object | failed courtship |
—
|
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: failed courtship | Statement: [Harold Mitch Mitchell, relationshipStatusWithBlanche, failed courtship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipStatusWithBlanche Context triple: [Harold Mitch Mitchell, relationshipStatusWithBlanche, failed courtship]
-
A.
relationshipToBlancheDevereaux
chosen
Indicates the specific type of personal or familial relationship an entity has with Blanche Devereaux.
-
B.
relationshipToBlancheDuBois
Indicates the specific familial, social, or interpersonal connection an entity has with Blanche DuBois.
-
C.
discoversAboutBlanche
Indicates that one entity comes to learn or find out information concerning Blanche.
-
D.
relationshipToBaudelaires
Indicates the type of personal or familial connection an entity has to the Baudelaires.
-
E.
relationshipToDésirée
Indicates the specific type of personal or social relationship that one entity has to Désirée.
- 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_69ef6a4f1d9c8190b0705acda054368d |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69ff7eb7189c81909a8f73fbc4c48e02 |
completed | May 9, 2026, 6:36 p.m. |
| PD | Predicate disambiguation | batch_69ff7e54e11081908fb5ce10c5aa7b53 |
completed | May 9, 2026, 6:35 p.m. |
Created at: April 27, 2026, 2:13 p.m.