Triple
T36019047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reginald Herbert, 15th Earl of Pembroke |
E1041932
|
entity |
| Predicate | successionNumberAsEarlOfMontgomery |
P202014
|
FINISHED |
| Object | 12 |
—
|
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: 12 | Statement: [Reginald Herbert, 15th Earl of Pembroke, successionNumberAsEarlOfMontgomery, 12]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successionNumberAsEarlOfMontgomery Context triple: [Reginald Herbert, 15th Earl of Pembroke, successionNumberAsEarlOfMontgomery, 12]
-
A.
successorAsEarlOfStrathearn
Indicates that one individual became the next Earl of Strathearn following another, succeeding them in that noble title.
-
B.
successionNumberAsEarlOfPembroke
Indicates the ordinal position an individual holds in the sequence of people who have held the title Earl of Pembroke.
-
C.
successorAsEarlOfMorton
Indicates the person who became the next Earl of Morton after the previous holder of the title.
-
D.
successorAsEarl
Indicates that one person became the next holder of the title of Earl after another person.
-
E.
successorAsEarlOfHuntingdon
Indicates that one person became the next Earl of Huntingdon following another person in that title or office.
- F. None of above. chosen
Provenance (4 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_69f76e2b981881908e4e160607fa82eb |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a0045a7b4c081908e4dedabda7cf790 |
completed | May 10, 2026, 8:45 a.m. |
| PD | Predicate disambiguation | batch_6a0042b148a48190974b173f352e4b7f |
completed | May 10, 2026, 8:32 a.m. |
| PDg | Predicate description generation | batch_6a0045a6ce788190913fa017097a15b8 |
completed | May 10, 2026, 8:45 a.m. |
Created at: May 3, 2026, 4:07 p.m.