Triple
T6040161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pelagos Sanctuary for Mediterranean Marine Mammals |
E134522
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object |
SPAMI
SPAMI is a specially protected marine area designation under the Barcelona Convention aimed at conserving important Mediterranean marine and coastal habitats and species.
|
E564724
|
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: SPAMI | Statement: [Pelagos Sanctuary for Mediterranean Marine Mammals, abbreviation, SPAMI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SPAMI Context triple: [Pelagos Sanctuary for Mediterranean Marine Mammals, abbreviation, SPAMI]
-
A.
SMI
SMI is the vehicle registration code assigned to the town of Mikołów in Poland.
-
B.
STM
STM is the public transit agency serving the city of Montreal, operating its bus and metro networks.
-
C.
STM
STM is the station code for Smithtown station, a Long Island Rail Road commuter rail stop in Smithtown, New York.
-
D.
STM
STM is the stock ticker symbol for STMicroelectronics, a major global semiconductor manufacturer.
-
E.
SPS
SPS is a high-energy circular particle accelerator at CERN that serves as a key injector for the Large Hadron Collider and supports a wide range of physics experiments.
- 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: SPAMI Triple: [Pelagos Sanctuary for Mediterranean Marine Mammals, abbreviation, SPAMI]
Generated description
SPAMI is a specially protected marine area designation under the Barcelona Convention aimed at conserving important Mediterranean marine and coastal habitats and species.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SPAMI Target entity description: SPAMI is a specially protected marine area designation under the Barcelona Convention aimed at conserving important Mediterranean marine and coastal habitats and species.
-
A.
SMI
SMI is the vehicle registration code assigned to the town of Mikołów in Poland.
-
B.
STM
STM is the public transit agency serving the city of Montreal, operating its bus and metro networks.
-
C.
STM
STM is the station code for Smithtown station, a Long Island Rail Road commuter rail stop in Smithtown, New York.
-
D.
STM
STM is the stock ticker symbol for STMicroelectronics, a major global semiconductor manufacturer.
-
E.
SPS
SPS is a high-energy circular particle accelerator at CERN that serves as a key injector for the Large Hadron Collider and supports a wide range of physics experiments.
- 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_69c00875db5c819099dd5bb833ec43c2 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c056cf82d481909d5161fe3643e7ed |
completed | March 22, 2026, 8:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c11393f4ec81909f175de55694b44e |
completed | March 23, 2026, 10:19 a.m. |
| NEDg | Description generation | batch_69c11560824081909d1228056607a3bd |
completed | March 23, 2026, 10:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c11607805c8190a9bc734479b1cb8d |
completed | March 23, 2026, 10:29 a.m. |
Created at: March 22, 2026, 4:08 p.m.