Triple
T37247106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sabina |
E923886
|
entity |
| Predicate | relationshipToHenryAntrobus |
P87836
|
FINISHED |
| Object | servant in the same household |
—
|
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: servant in the same household | Statement: [Sabina, relationshipToHenryAntrobus, servant in the same household]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToHenryAntrobus Context triple: [Sabina, relationshipToHenryAntrobus, servant in the same household]
-
A.
relationshipToHenry
chosen
Indicates the specific type of relationship or connection that an entity has to Henry.
-
B.
relationshipTypeWithHenryWilcox
Indicates the specific nature or category of relationship that an entity has with Henry Wilcox.
-
C.
relationshipWithHarold
Indicates that an entity has some form of personal, social, or professional relationship with Harold.
-
D.
relationshipToEleanorVance
Indicates the specific nature or type of relationship an entity has with Eleanor Vance.
-
E.
relationshipToHarryBosch
Indicates the specific familial, professional, or personal relationship that one entity has to Harry Bosch.
- 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_69f76eaabb4c819093b751b139dad551 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:15 p.m.