Triple

T10745888
Position Surface form Disambiguated ID Type / Status
Subject Lacq gas field E253447 entity
Predicate discoveredBy P412 FINISHED
Object SNPA
SNPA (Société Nationale des Pétroles d’Aquitaine) was a French state-owned oil and gas company best known for its role in exploring and developing major hydrocarbon fields in southwestern France.
E883895 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: SNPA | Statement: [Lacq gas field, discoveredBy, SNPA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SNPA
Context triple: [Lacq gas field, discoveredBy, SNPA]
  • A. SNASPE
    SNASPE is Chile’s national network of protected wild areas, encompassing national parks, reserves, and natural monuments managed to conserve the country’s biodiversity and ecosystems.
  • B. SPN
    SPN is the IATA airport code for Saipan International Airport, the main air gateway to Saipan in the Northern Mariana Islands.
  • C. SPN
    SPN is the National Rail station code for Spooner Row railway station in Norfolk, England.
  • D. SPN
    SPN is the vehicle registration code used on license plates for the town of Spremberg in Germany.
  • E. SNA
    SNA is the IATA airport code for John Wayne Airport, a commercial and general aviation airport serving Orange County, California.
  • 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: SNPA
Triple: [Lacq gas field, discoveredBy, SNPA]
Generated description
SNPA (Société Nationale des Pétroles d’Aquitaine) was a French state-owned oil and gas company best known for its role in exploring and developing major hydrocarbon fields in southwestern France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SNPA
Target entity description: SNPA (Société Nationale des Pétroles d’Aquitaine) was a French state-owned oil and gas company best known for its role in exploring and developing major hydrocarbon fields in southwestern France.
  • A. SNASPE
    SNASPE is Chile’s national network of protected wild areas, encompassing national parks, reserves, and natural monuments managed to conserve the country’s biodiversity and ecosystems.
  • B. SPN
    SPN is the IATA airport code for Saipan International Airport, the main air gateway to Saipan in the Northern Mariana Islands.
  • C. SPN
    SPN is the vehicle registration code used on license plates for the town of Spremberg in Germany.
  • D. SPN
    SPN is the National Rail station code for Spooner Row railway station in Norfolk, England.
  • E. SNA
    SNA is the IATA airport code for John Wayne Airport, a commercial and general aviation airport serving Orange County, California.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d711b77c4881909d16c6e82a9b86ca completed April 9, 2026, 2:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69de230b461c81909a98085079676b95 completed April 14, 2026, 11:20 a.m.
NEDg Description generation batch_69de271e2698819093bba748a0a0db5d completed April 14, 2026, 11:38 a.m.
NED2 Entity disambiguation (via description) batch_69de2cdd79608190bad8045939556bc7 completed April 14, 2026, 12:02 p.m.
Created at: April 8, 2026, 9:15 p.m.