Triple
T30068749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clarinda |
E764114
|
entity |
| Predicate | correspondencePartnerRealName |
P146116
|
FINISHED |
| Object | Robert Burns |
—
|
NE NERFINISHED |
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: Robert Burns | Statement: [Clarinda, correspondencePartnerRealName, Robert Burns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: correspondencePartnerRealName Context triple: [Clarinda, correspondencePartnerRealName, Robert Burns]
-
A.
otherRepresentedParty
Indicates that one party is acting or being represented on behalf of another, distinct party in a given context or transaction.
-
B.
correspondenceRelationshipWith
chosen
Indicates a relationship in which two entities are connected through the exchange or maintenance of correspondence (such as letters, messages, or other communications).
-
C.
associatedName
Indicates that one entity has an alternative or related name that is linked or connected to another entity.
-
D.
spouseRealName
Indicates that one person is the legally recognized spouse of another, using the spouse’s real (non-alias) name.
-
E.
hasFormerPartnerName
Indicates that an entity has the recorded name of a person or organization who was previously their partner.
- 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_69f2247221388190a13a22c47094a0ef |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6db1f3ec48190a82e7d893d3c76ba |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82adfa481908a5e196d2e18c73f |
completed | May 3, 2026, 5:07 a.m. |
Created at: April 29, 2026, 7 p.m.