Triple
T27554294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Battles of the Fords of Isen |
E695591
|
entity |
| Predicate | featuresPeople |
P193877
|
FINISHED |
| Object | Riders of Rohan |
—
|
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: Riders of Rohan | Statement: [The Battles of the Fords of Isen, featuresPeople, Riders of Rohan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresPeople Context triple: [The Battles of the Fords of Isen, featuresPeople, Riders of Rohan]
-
A.
featuresResponseOfPeople
Indicates a relationship where something presents or includes the reactions, opinions, or feedback expressed by people.
-
B.
featuresLeader
Indicates that one entity includes, presents, or highlights another entity in the role of a leader.
-
C.
primaryPeople
Indicates that the referenced people are the main or most important individuals associated with a given entity, event, or context.
-
D.
metPerson
Indicates that one person has encountered or come into contact with another person, typically in a face-to-face meeting.
-
E.
featuresHero
Indicates that something (such as a work, product, or story) prominently includes or centers around a particular hero as a main character or focus.
- F. None of above. chosen
Provenance (4 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_69ef5387e97c8190a9dab040d21cd048 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fd592e48cc81909d754cc6c4bd99ae |
completed | May 8, 2026, 3:31 a.m. |
| PD | Predicate disambiguation | batch_69fd58b7f9b881909dc099b28d567784 |
completed | May 8, 2026, 3:30 a.m. |
| PDg | Predicate description generation | batch_69fd592cc56081908ce456114d407616 |
completed | May 8, 2026, 3:31 a.m. |
Created at: April 27, 2026, 1:36 p.m.