Triple
T15313295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Octopus |
E366091
|
entity |
| Predicate | engineManufacturer |
P4022
|
FINISHED |
| Object | MTU |
E745146
|
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: MTU | Statement: [Octopus, engineManufacturer, MTU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MTU Context triple: [Octopus, engineManufacturer, MTU]
-
A.
MTU
MTU is a major engineering and technological university located in Mandalay, Myanmar, known for training engineers and conducting applied research.
-
B.
MTU
MTU is a public research university in Houghton, Michigan, known for its strong engineering, technology, and science programs.
-
C.
MTU
chosen
MTU is a German brand best known for its high-performance diesel engines and propulsion systems used in marine, industrial, and power generation applications.
-
D.
MTC
MTC is the station code for Meerut City railway station, a major rail hub in the city of Meerut, Uttar Pradesh, India.
-
E.
MTC
MTC is a regional planning and transportation agency that coordinates and funds transit, highways, and other mobility projects in the San Francisco Bay Area.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03cd2d5a88190aead748920f93d47 |
completed | April 16, 2026, 1:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fef8a3da3881909b50cfbec0543adc |
completed | May 9, 2026, 9:04 a.m. |
Created at: April 10, 2026, 3:16 a.m.