Triple
T15673166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herbert Head |
E377368
|
entity |
| Predicate | relationshipToCompsonFamily |
P89441
|
FINISHED |
| Object | in-law |
—
|
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: in-law | Statement: [Herbert Head, relationshipToCompsonFamily, in-law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToCompsonFamily Context triple: [Herbert Head, relationshipToCompsonFamily, in-law]
-
A.
relationshipToCaddyCompson
Indicates the specific familial or interpersonal relationship that an entity has to Caddy Compson.
-
B.
familyConnectionTo
chosen
Indicates a familial relationship or bond that exists between two entities, such as by blood, marriage, or adoption.
-
C.
associatedWithComposerFamily
Indicates that an entity has a relationship or connection to a family of composers, such as belonging to, working with, or being otherwise linked to that composer family.
-
D.
relationshipToRelative
Indicates the specific familial connection or kinship role that one person has in relation to a particular relative.
-
E.
relationshipToMother
Indicates the specific familial or social connection an entity has to its mother.
- 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_69d85cd2e28481909d4e975bee20872f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04f2c996c8190a9ebe0e92608feaa |
completed | April 16, 2026, 2:53 a.m. |
| PD | Predicate disambiguation | batch_69deda8b36a4819081cb5708fe77ef51 |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:16 a.m.