Triple
T19100949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Piemur |
E467527
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Sebell |
—
|
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: Sebell | Statement: [Piemur, friend, Sebell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sebell Context triple: [Piemur, friend, Sebell]
-
A.
Sebell
chosen
Sebell is a fictional Master Harper from Anne McCaffrey’s Dragonriders of Pern series, known for his musical talent, diplomacy, and role in uncovering Pern’s ancient history.
-
B.
Seirah
Seirah is a biblical location mentioned in the Hebrew Bible as a place of refuge associated with the judge Ehud.
-
C.
Seir
Seir is a mountainous region in Edom, traditionally associated with the Horites and later the descendants of Esau in the Hebrew Bible.
-
D.
Sibinal
Sibinal is a highland municipality in western Guatemala’s San Marcos Department, known for its rural communities and proximity to the Tacaná volcano near the Mexican border.
-
E.
Servaas
Servaas is the Dutch name for Saint Servatius of Tongeren-Maastricht, a 4th-century Christian bishop venerated as a patron saint in parts of the Low Countries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e36de7bc8190b353ed59e12e4631 |
completed | April 20, 2026, 8:27 a.m. |
Created at: April 10, 2026, 12:04 p.m.