Triple
T29057953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1st Marquess of Milford Haven |
E735442
|
entity |
| Predicate | anglicizedFamilyName |
P87582
|
FINISHED |
| Object | Mountbatten |
—
|
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: Mountbatten | Statement: [1st Marquess of Milford Haven, anglicizedFamilyName, Mountbatten]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: anglicizedFamilyName Context triple: [1st Marquess of Milford Haven, anglicizedFamilyName, Mountbatten]
-
A.
dynasticSurnameAnglicisedAs
chosen
Indicates that a dynastic surname has an established or commonly used anglicized form derived from its original language.
-
B.
familyName
Indicates that one entity is the family (last) name associated with another entity (typically a person).
-
C.
nameFamily
Indicates that one entity is the family name (surname) of another entity.
-
D.
familyNamePattern
Indicates that there is a specific structural or formatting pattern that a family name (surname) follows.
-
E.
familyNamePart
Indicates that one string is a component or segment of a person's full family 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_69f077e85498819088b65186550da8cd |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f6609457148190aa52f24617101f50 |
completed | May 2, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69f659d297cc8190b2b962ba30a1edb3 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 10:13 a.m.