Triple
T12408274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eric Bates |
E296444
|
entity |
| Predicate | relationshipTypeWithJackBrown |
P94549
|
FINISHED |
| Object | owner-companion |
—
|
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: owner-companion | Statement: [Eric Bates, relationshipTypeWithJackBrown, owner-companion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithJackBrown Context triple: [Eric Bates, relationshipTypeWithJackBrown, owner-companion]
-
A.
relationshipToJackBrown
chosen
Indicates the specific familial, social, or professional relationship that an entity has to Jack Brown.
-
B.
relationshipTypeWithJakeBarnes
Indicates the specific nature or category of relationship that an entity has with Jake Barnes.
-
C.
relationshipToJamesBrown
Indicates the type of personal, professional, or familial relationship that an entity has with James Brown.
-
D.
relationshipType
Indicates the specific kind of relationship that exists between two or more entities.
-
E.
relationshipTypeWith Alicia Johns
Indicates the specific type or nature of the relationship that an entity has with Alicia Johns.
- 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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94e1888b48190bd750f839a26e99e |
completed | April 10, 2026, 7:23 p.m. |
| PD | Predicate disambiguation | batch_69d94d354b488190adc83fb4f2770dd5 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.