Triple
T13891616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Intercidades |
E333984
|
entity |
| Predicate | operator |
P179
|
FINISHED |
| Object |
CP Longo Curso
CP Longo Curso is the long-distance division of Portugal’s national railway company, responsible for operating Intercidades and other mainline passenger train services.
|
E1068971
|
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: CP Longo Curso | Statement: [Intercidades, operator, CP Longo Curso]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CP Longo Curso Context triple: [Intercidades, operator, CP Longo Curso]
-
A.
Longo
Longo is an Italian surname borne by various notable figures in politics, arts, and sports.
-
B.
Longu
Longu is an Austronesian language spoken in the Solomon Islands, known primarily as a local name for the Longgu language.
-
C.
Kurs-P
Kurs-P is a modernized, digital version of the Russian Kurs spacecraft docking system used to enable automated rendezvous and docking of visiting vehicles with space stations.
-
D.
Long Reth
Long Reth is an alternative name used by Nuon Chea, the former chief ideologue and "Brother Number Two" of Cambodia's Khmer Rouge regime.
-
E.
LongRun
LongRun is Transmeta's dynamic power management technology designed to reduce energy consumption and heat in microprocessors by adjusting voltage and clock speed on the fly.
- 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: CP Longo Curso Triple: [Intercidades, operator, CP Longo Curso]
Generated description
CP Longo Curso is the long-distance division of Portugal’s national railway company, responsible for operating Intercidades and other mainline passenger train services.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: CP Longo Curso Target entity description: CP Longo Curso is the long-distance division of Portugal’s national railway company, responsible for operating Intercidades and other mainline passenger train services.
-
A.
Longo
Longo is an Italian surname borne by various notable figures in politics, arts, and sports.
-
B.
Longu
Longu is an Austronesian language spoken in the Solomon Islands, known primarily as a local name for the Longgu language.
-
C.
Kurs-P
Kurs-P is a modernized, digital version of the Russian Kurs spacecraft docking system used to enable automated rendezvous and docking of visiting vehicles with space stations.
-
D.
Long Reth
Long Reth is an alternative name used by Nuon Chea, the former chief ideologue and "Brother Number Two" of Cambodia's Khmer Rouge regime.
-
E.
LongRun
LongRun is Transmeta's dynamic power management technology designed to reduce energy consumption and heat in microprocessors by adjusting voltage and clock speed on the fly.
- 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_69d81c5dd2d48190b7a5fc1e009de936 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de23a537d4819093c2bae2a244816a |
completed | April 14, 2026, 11:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c71a43908190bc7537f0a2379599 |
completed | May 3, 2026, 10:07 p.m. |
| NEDg | Description generation | batch_69f7c8d477f881908f8cfd2783e7f10f |
completed | May 3, 2026, 10:14 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f7ca27ffd4819080bccd6bfd88ddb3 |
completed | May 3, 2026, 10:20 p.m. |
Created at: April 9, 2026, 10:15 p.m.