Triple
T10152728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Crocker-Harris |
E232686
|
entity |
| Predicate | relationshipTypeWithMillieCrockerHarris |
P61001
|
FINISHED |
| Object | unhappy marriage |
—
|
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: unhappy marriage | Statement: [Andrew Crocker-Harris, relationshipTypeWithMillieCrockerHarris, unhappy marriage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithMillieCrockerHarris Context triple: [Andrew Crocker-Harris, relationshipTypeWithMillieCrockerHarris, unhappy marriage]
-
A.
relationshipToAndrewCrockerHarris
chosen
Indicates that one entity has a specified personal or social relationship to Andrew Crocker Harris.
-
B.
relationshipToHenry
Indicates the specific type of relationship or connection that an entity has to Henry.
-
C.
relationshipToHannah
Indicates the specific type of relationship or connection that an entity has to Hannah.
-
D.
hasFamilialTieTo
Indicates a relationship where two entities are connected by family bonds, such as by blood, marriage, or adoption.
-
E.
inRelationshipWith
Indicates that two entities are mutually involved in a defined personal, romantic, or partnership relationship with each other.
- 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_69ca84885e48819088a31b127cf44904 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cdec361c7c8190b8fd841d728d5bbe |
completed | April 2, 2026, 4:10 a.m. |
| PD | Predicate disambiguation | batch_69cd4ba4f5d88190ba68e63be10b08c7 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:08 p.m.