Triple
T30138881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baron Lang of Lambeth |
E766071
|
entity |
| Predicate | holderClericalTitle |
P3342
|
FINISHED |
| Object | Archbishop of Canterbury |
—
|
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: Archbishop of Canterbury | Statement: [Baron Lang of Lambeth, holderClericalTitle, Archbishop of Canterbury]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holderClericalTitle Context triple: [Baron Lang of Lambeth, holderClericalTitle, Archbishop of Canterbury]
-
A.
holderFullTitle
Indicates that one entity is the complete, formal title or designation held by another entity.
-
B.
officeHolderTitle
chosen
Indicates the official position or title held by a person in an office or role.
-
C.
heldTitleUnder
Indicates that one entity possessed or occupied a particular title, rank, or office under the authority, jurisdiction, or auspices of another entity.
-
D.
titleHeldAs
Indicates that an entity holds or possesses a specific title in a particular capacity or role.
-
E.
heldCourtesyTitle
Indicates that an entity temporarily bore or used an honorary or courtesy title without holding the substantive rank or office associated with it.
- 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_69f2247909048190ae86c2160cf8b566 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67e86d38c8190a100b82da345b6ca |
completed | May 2, 2026, 10:45 p.m. |
| PD | Predicate disambiguation | batch_69f675ff62c48190a634bbb8896973b9 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:17 p.m.