Triple
T27306655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viscount Bruce |
E689078
|
entity |
| Predicate | firstHolderHonour |
P153898
|
FINISHED |
| Object | Companion of Honour |
—
|
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: Companion of Honour | Statement: [Viscount Bruce, firstHolderHonour, Companion of Honour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstHolderHonour Context triple: [Viscount Bruce, firstHolderHonour, Companion of Honour]
-
A.
first_holder
chosen
Indicates that the subject is the earliest or original holder or possessor of the specified object, title, or right.
-
B.
firstHeldAs
Indicates the initial time or context in which an entity was first possessed, owned, or held by another entity.
-
C.
honoursHolder
Indicates that one entity is the designated recipient or bearer of a particular honour, award, or distinction conferred by another entity.
-
D.
firstHolderParty
Indicates that the referenced party is the initial or original holder in the specified relationship or arrangement.
-
E.
firstHolderInCanon
Indicates that the subject is the earliest entity, in the canonical timeline or storyline, known to have held or possessed the specified object, title, or role.
- 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_69ef355b931c8190a63cafaf7bcc008b |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69ff0d80c0dc81909fbd12285c7a45c0 |
completed | May 9, 2026, 10:33 a.m. |
| PD | Predicate disambiguation | batch_69ff0cd03e78819094895058f925fbfa |
completed | May 9, 2026, 10:30 a.m. |
Created at: April 27, 2026, 11:25 a.m.