Triple
T27231706
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord Chief Justice of Ireland |
E682170
|
entity |
| Predicate | usedHonorificallyFor |
P119748
|
FINISHED |
| Object | head of the Irish bench |
—
|
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: head of the Irish bench | Statement: [Lord Chief Justice of Ireland, usedHonorificallyFor, head of the Irish bench]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedHonorificallyFor Context triple: [Lord Chief Justice of Ireland, usedHonorificallyFor, head of the Irish bench]
-
A.
usedHonorificallySince
Indicates that an honorific form of address or title has been in use for referring to the entity since a specified point in time.
-
B.
honorificUse
chosen
Indicates that one entity refers to or addresses another using an honorific title or respectful linguistic form.
-
C.
honorificUsage
Indicates that one entity refers to or addresses another using an honorific title or respectful linguistic form.
-
D.
honorificSense
Indicates that one entity refers to another using an honorific or respectful linguistic form.
-
E.
usedHonorificInBranding
Indicates that an entity employed an honorific title (e.g., “Dr.”, “Sir”) as part of its branding, naming, or marketing presentation.
- 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_69eefacdad7881908b7bca61c90a1a1e |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f6264ec31081908b14cbdbc604d437 |
completed | May 2, 2026, 4:29 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 9:46 a.m.