Triple
T7985635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apache Hive |
E185675
|
entity |
| Predicate | supportsFileFormat |
P8463
|
FINISHED |
| Object | ORC |
E97127
|
NE 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: ORC | Statement: [Apache Hive, supportsFileFormat, ORC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ORC Context triple: [Apache Hive, supportsFileFormat, ORC]
-
A.
ORC
chosen
ORC (Optimized Row Columnar) is a highly efficient, columnar storage file format commonly used in big data systems to enable fast analytics and compression.
-
B.
ORC
ORC is the abbreviation for the Organized Reserve Corps, a former component of the United States Army Reserve structure.
-
C.
ORCP
ORCP is the standard legal abbreviation for the Oregon Rules of Civil Procedure, which govern civil court proceedings in the state of Oregon.
-
D.
ORI
ORI is a revolutionary political organization known for uniting various radical groups under a single integrated movement.
-
E.
ORCA
ORCA is a widely used, versatile quantum chemistry software package known for its efficient and accurate implementations of electronic structure methods, including density functional theory.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca829a2cfc819083d591d58ec04075 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c4a55b881909a96133e56c0dffa |
completed | March 31, 2026, 3:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe0e6f3c48190a0132fa90eec6420 |
completed | March 31, 2026, 2:57 p.m. |
Created at: March 30, 2026, 5:15 p.m.