Triple
T9636423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sailor King |
E232943
|
entity |
| Predicate | hasOrdinalOfReferent |
P64649
|
FINISHED |
| Object | IV |
—
|
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: IV | Statement: [Sailor King, hasOrdinalOfReferent, IV]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOrdinalOfReferent Context triple: [Sailor King, hasOrdinalOfReferent, IV]
-
A.
hasOrdinalSeries
Indicates that one entity belongs to, or is positioned within, an ordered sequence or series relative to other entities.
-
B.
hasNotableBearerOrdinalNumber
chosen
Indicates that an entity is associated with a notable bearer identified by a specific ordinal position (e.g., first, second, third) among others with the same name or title.
-
C.
hasMainReferent
Indicates that one entity serves as the primary or central referent for another entity within a given context.
-
D.
hasAlternativeReferent
Indicates that an entity can also be referred to or identified by an alternative name, label, or reference.
-
E.
isOrdinaryOf
Indicates that one entity is the standard, non-special, or typical instance or form of 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_69ca848940cc8190b97cec654cb3bb4a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b5045cc8190ab717f42d803e010 |
completed | April 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69ccd5acfa5c8190aaba3cf548723604 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:11 p.m.