Triple
T29477238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dernhelm |
E747681
|
entity |
| Predicate | purposeOfAlias |
P92674
|
FINISHED |
| Object | to join the Rohirrim in battle secretly |
—
|
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: to join the Rohirrim in battle secretly | Statement: [Dernhelm, purposeOfAlias, to join the Rohirrim in battle secretly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: purposeOfAlias Context triple: [Dernhelm, purposeOfAlias, to join the Rohirrim in battle secretly]
-
A.
reasonForAlias
chosen
Indicates the justification or underlying cause for which an entity uses or is assigned a particular alias.
-
B.
subjectAlias
Indicates that one entity is an alternative name, label, or alias referring to the same subject as another entity.
-
C.
usesAliasFor
Indicates that one entity employs an alternative name or identifier to refer to another entity.
-
D.
notationPurpose
Indicates that one notation is used with the specific purpose or function of representing, explaining, or supporting another entity or concept.
-
E.
featuresAlias
Indicates that one entity is used as an alternative name or label (an alias) for another entity.
- 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_69f0bd42cf308190bb01b20bc5b7c2d0 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66bd57cac81909e92d58fb91b4a5c |
completed | May 2, 2026, 9:25 p.m. |
| PD | Predicate disambiguation | batch_69f66339175c819080bd70f0ff7057b1 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 4:01 p.m.