Triple
T25999045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fen-Edebiyat Fakültesi |
E646567
|
entity |
| Predicate | disiplin |
P159651
|
FINISHED |
| Object | fizik |
—
|
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: fizik | Statement: [Fen-Edebiyat Fakültesi, disiplin, fizik]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disiplin Context triple: [Fen-Edebiyat Fakültesi, disiplin, fizik]
-
A.
disiplin
chosen
Indicates a relationship where one entity enforces or maintains discipline over another, or where an action involves applying or upholding disciplinary rules.
-
B.
attractsDiscipline
Indicates a relationship where one entity draws or brings about discipline, order, or self-control in another entity.
-
C.
partyDiscipline
Indicates the extent to which members of a political party consistently follow and support the party’s official positions, rules, and leadership directives in their actions or decisions.
-
D.
regulatesDiscipline
Indicates that one entity establishes or enforces rules, standards, or controls governing the conduct or discipline of another entity.
-
E.
dominatedDiscipline
Indicates that one entity exerted controlling power or authority over another within a specific discipline or field.
- 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_69e77e88cb8481908da31d4a00661f55 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f605720be48190b1b64ecdccfaec17 |
completed | May 2, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 8:58 a.m.