Triple
T31698647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pam Halpert |
E808987
|
entity |
| Predicate | fullMaidenName |
P36176
|
FINISHED |
| Object | Pamela Morgan Beesly |
—
|
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: Pamela Morgan Beesly | Statement: [Pam Halpert, fullMaidenName, Pamela Morgan Beesly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fullMaidenName Context triple: [Pam Halpert, fullMaidenName, Pamela Morgan Beesly]
-
A.
fullLegalName
Indicates that the associated value is the complete, official legal name of the entity as recognized by law or formal records.
-
B.
fullGivenNameOf
Indicates that one entity is the complete, formal given name corresponding to another entity (such as a person or identifier).
-
C.
maidenNameOf
chosen
Indicates that one person’s original family surname before marriage is the maiden name of another person.
-
D.
fullCaseName
Indicates that one entity is the complete, formal name of a legal case associated with another entity.
-
E.
fullName
Indicates that an entity has a complete personal name, typically combining given name(s) and family name into a single string.
- 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_69f348de914081909fc8edff56f34dbe |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:11 p.m.