Triple
T9871759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Eastman |
E239972
|
entity |
| Predicate | legalNameChange |
P60795
|
FINISHED |
| Object | changed surname from Epstein to Eastman |
—
|
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: changed surname from Epstein to Eastman | Statement: [Lee Eastman, legalNameChange, changed surname from Epstein to Eastman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalNameChange Context triple: [Lee Eastman, legalNameChange, changed surname from Epstein to Eastman]
-
A.
officialNameChangeTo
chosen
Indicates that an entity’s official name has been changed from a previous name to a new specified name.
-
B.
changedSurnameFrom
Indicates that an entity has adopted a new surname that was previously a different, specified surname.
-
C.
changedSurnameTo
Indicates that an entity has adopted a new surname, replacing their previous one, with the new surname specified as the related entity.
-
D.
changedNameOn
Indicates that an entity altered or updated its name at a specific point in time or on a particular date.
-
E.
nameChangeReason
Indicates the reason or justification for a change in an entity’s name.
- 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_69ca84e7506c819095cbde4ff16512bb |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3f5cc948190b03186b867c92229 |
completed | April 2, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69cd1d7621d48190aa6a6f34399514b0 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:36 p.m.