Triple
T6338207
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GTC |
E142548
|
entity |
| Predicate | hasPrefixFormat |
P66954
|
FINISHED |
| Object | XXX (three-letter prefix) |
—
|
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: XXX (three-letter prefix) | Statement: [GTC, hasPrefixFormat, XXX (three-letter prefix)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrefixFormat Context triple: [GTC, hasPrefixFormat, XXX (three-letter prefix)]
-
A.
hasPrefix
chosen
Indicates that one entity occurs at the beginning of another entity, serving as its starting segment or initial substring.
-
B.
hasFormatElement
Indicates that one entity includes, is composed of, or is associated with a specific structural or formatting component of its overall format.
-
C.
hasMatchFormat
Indicates that something (such as a game, event, or competition) is conducted according to a specified match format or structure.
-
D.
hasFormatCurrent
Indicates that an entity is available or expressed in the currently used or most up-to-date format.
-
E.
hasOriginalPrefix
Indicates that an entity retains or is associated with its initial or primary prefix from which later forms or variants are derived.
- 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_69c008d4d8e88190ad301c05b08722ac |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0654e11988190b708426d3003716a |
completed | March 22, 2026, 9:55 p.m. |
| PD | Predicate disambiguation | batch_69c060e7e2d48190af9d004236466788 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:30 p.m.