Triple
T22133987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haderslev Katedralskole |
E546977
|
entity |
| Predicate | hasAbbreviation |
P43
|
FINISHED |
| Object |
HADKAT
HADKAT is the commonly used abbreviation for Haderslev Katedralskole, a historic upper secondary school in Haderslev, Denmark.
|
E1519871
|
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: HADKAT | Statement: [Haderslev Katedralskole, hasAbbreviation, HADKAT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HADKAT Context triple: [Haderslev Katedralskole, hasAbbreviation, HADKAT]
-
A.
Hadl
Hadl is the surname of John Hadl, a notable American football quarterback who played primarily for the San Diego Chargers in the AFL and NFL.
-
B.
HAD
HAD is the commonly used abbreviation for the Historical Astronomy Division, a group focused on the study and promotion of the history of astronomy.
-
C.
HAD
HAD is the station code used to identify Hallunda metro station in the Stockholm Metro system.
-
D.
Hatsekats
Hatsekats is a village in Armenia known historically as the birthplace of the Armenian alphabet creator Mesrop Mashtots.
-
E.
Darkhad
The Darkhad are a Mongolic ethnic group traditionally known as pastoral nomads and guardians of sacred sites in northern and western Mongolia.
- 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: HADKAT Triple: [Haderslev Katedralskole, hasAbbreviation, HADKAT]
Generated description
HADKAT is the commonly used abbreviation for Haderslev Katedralskole, a historic upper secondary school in Haderslev, Denmark.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: HADKAT Target entity description: HADKAT is the commonly used abbreviation for Haderslev Katedralskole, a historic upper secondary school in Haderslev, Denmark.
-
A.
Hadl
Hadl is the surname of John Hadl, a notable American football quarterback who played primarily for the San Diego Chargers in the AFL and NFL.
-
B.
HAD
HAD is the commonly used abbreviation for the Historical Astronomy Division, a group focused on the study and promotion of the history of astronomy.
-
C.
HAD
HAD is the station code used to identify Hallunda metro station in the Stockholm Metro system.
-
D.
Hatsekats
Hatsekats is a village in Armenia known historically as the birthplace of the Armenian alphabet creator Mesrop Mashtots.
-
E.
Darkhad
The Darkhad are a Mongolic ethnic group traditionally known as pastoral nomads and guardians of sacred sites in northern and western Mongolia.
- 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_69e11e39bf348190b541bfa16a7b71e0 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129b8f4248190b6342c8d00942c25 |
completed | April 28, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a8f2bd49c81908a75359074a0ada2 |
completed | May 18, 2026, 4:01 a.m. |
| NEDg | Description generation | batch_6a0a91ef8d188190a6ec20d6c43aef91 |
completed | May 18, 2026, 4:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a9266624c81908eb06a0fc02b85d4 |
completed | May 18, 2026, 4:15 a.m. |
Created at: April 16, 2026, 8:32 p.m.