Triple
T16257491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Venus Express |
E394668
|
entity |
| Predicate | launchContractor |
P31843
|
FINISHED |
| Object | Starsem |
E962781
|
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: Starsem | Statement: [Venus Express, launchContractor, Starsem]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Starsem Context triple: [Venus Express, launchContractor, Starsem]
-
A.
Starsem
chosen
Starsem is a European-Russian joint venture that commercializes Soyuz launch services, primarily for international satellite customers.
-
B.
Imtech
Imtech was a European technical services provider specializing in electrical engineering, ICT, and mechanical services for buildings and industry.
-
C.
Indra Sistemas
Indra Sistemas is a Spanish multinational technology and defense company specializing in information technology, simulation, and advanced electronic systems for civil and military applications.
-
D.
Cymer
Cymer is a leading supplier of light sources for semiconductor lithography systems, best known for providing the laser technology used in advanced chip manufacturing.
-
E.
Asiatech
Asiatech was a short-lived Formula One engine manufacturer that supplied customer engines in the early 2000s after acquiring Peugeot’s F1 engine program.
- 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2459b1624819086bf681075097235 |
completed | April 17, 2026, 2:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a000eebcfe481909822290d3a7b361c |
completed | May 10, 2026, 4:51 a.m. |
Created at: April 10, 2026, 5:04 a.m.