Triple
T29021872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | McLaren F1 |
E737470
|
entity |
| Predicate | engineModel |
P2092
|
FINISHED |
| Object |
BMW S70/2
The BMW S70/2 is a high-performance 6.1-liter naturally aspirated V12 engine developed by BMW Motorsport, best known for powering the legendary McLaren F1 supercar.
|
E1844011
|
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: BMW S70/2 | Statement: [McLaren F1, engineModel, BMW S70/2]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: BMW S70/2 Triple: [McLaren F1, engineModel, BMW S70/2]
Generated description
The BMW S70/2 is a high-performance 6.1-liter naturally aspirated V12 engine developed by BMW Motorsport, best known for powering the legendary McLaren F1 supercar.
Provenance (5 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_69f077ee19f881909af48f9cab00a2e5 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f66005ea00819085501231fe82cc5e |
completed | May 2, 2026, 8:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2505d18e5c8190a57b2fc092cae0d5 |
completed | June 7, 2026, 5:46 a.m. |
| NEDg | Description generation | batch_6a2509d5f290819094bf3f206d31f901 |
completed | June 7, 2026, 6:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a250c110ff881908e8de595a2592a3e |
completed | June 7, 2026, 6:13 a.m. |
Created at: April 28, 2026, 9:49 a.m.