Triple

T18641523
Position Surface form Disambiguated ID Type / Status
Subject Serena Ventures E455697 entity
Predicate portfolioCompany P43497 FINISHED
Object Alma
Alma is a startup backed by Serena Ventures, likely operating in a high-growth, innovation-focused sector aligned with the fund’s investment themes.
 E1334758 NE FINISHED

How this triple was built (4 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: Alma | Statement: [Serena Ventures, portfolioCompany, Alma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Alma
Context triple: [Serena Ventures, portfolioCompany, Alma]
  • A. Alma
    Alma is a historic wooden scow schooner preserved as a museum ship in San Francisco, representing the city’s 19th- and early 20th-century maritime commerce.
  • B. Alma
    Alma is a historic British Army battle honour commemorating the Battle of the Alma in the Crimean War.
  • C. Alma
    Alma is a feminine given name of Latin origin meaning "nourishing" or "kind," used in various cultures around the world.
  • D. Alma
    Alma is a small industrial and service city in Quebec, Canada, located in the Saguenay–Lac-Saint-Jean region and known for its aluminum production and proximity to Lac Saint-Jean.
  • E. Alma Jr.
    Alma Jr. is a fictional character from the film and short story "Brokeback Mountain," the daughter of Ennis Del Mar and Alma Beers Del Mar.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Alma
Triple: [Serena Ventures, portfolioCompany, Alma]
Generated description
Alma is a startup backed by Serena Ventures, likely operating in a high-growth, innovation-focused sector aligned with the fund’s investment themes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Alma
Target entity description: Alma is a startup backed by Serena Ventures, likely operating in a high-growth, innovation-focused sector aligned with the fund’s investment themes.
  • A. Alma
    Alma is a historic wooden scow schooner preserved as a museum ship in San Francisco, representing the city’s 19th- and early 20th-century maritime commerce.
  • B. Alma
    Alma is a historic British Army battle honour commemorating the Battle of the Alma in the Crimean War.
  • C. Alma
    Alma is a feminine given name of Latin origin meaning "nourishing" or "kind," used in various cultures around the world.
  • D. Alma
    Alma is a small industrial and service city in Quebec, Canada, located in the Saguenay–Lac-Saint-Jean region and known for its aluminum production and proximity to Lac Saint-Jean.
  • E. Alma Jr.
    Alma Jr. is a fictional character from the film and short story "Brokeback Mountain," the daughter of Ennis Del Mar and Alma Beers Del Mar.
  • F. None of above. chosen

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_69d8d38ea1e88190997e9b231190ba6f completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54fccafec8190a340356d5bbd3cdf completed April 19, 2026, 9:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a050d8447e48190b496903add62b2bb completed May 13, 2026, 11:47 p.m.
NEDg Description generation batch_6a050f560d088190bd23765330dcef47 completed May 13, 2026, 11:55 p.m.
NED2 Entity disambiguation (via description) batch_6a050fc2dd2c81909e3c929f57b299d5 completed May 13, 2026, 11:56 p.m.
Created at: April 10, 2026, 11:47 a.m.