Triple
T4328132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gangmasters and Labour Abuse Authority |
E96680
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object |
GLAA
GLAA is a UK government body responsible for licensing labour providers and investigating labour exploitation and modern slavery in high-risk sectors.
|
E431669
|
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: GLAA | Statement: [Gangmasters and Labour Abuse Authority, shortName, GLAA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GLAA Context triple: [Gangmasters and Labour Abuse Authority, shortName, GLAA]
-
A.
Gla
Gla is a large fortified Mycenaean archaeological site in Boeotia, Greece, notable for its massive walls and strategic position overlooking the former Lake Kopais.
-
B.
GLA
GLA is the three-letter IATA airport code for Glasgow Airport, the main international airport serving Glasgow, Scotland.
-
C.
Gliz
Gliz is one of the official mascots of the 2006 Winter Olympics in Turin, Italy, depicted as a stylized anthropomorphic ice cube symbolizing winter sports and modernity.
-
D.
GCLA
GCLA is the ICAO airport code for La Palma Airport in Spain’s Canary Islands.
-
E.
Lama glama
Lama glama is the domesticated South American camelid commonly known as the llama, used as a pack animal and for its wool.
- 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: GLAA Triple: [Gangmasters and Labour Abuse Authority, shortName, GLAA]
Generated description
GLAA is a UK government body responsible for licensing labour providers and investigating labour exploitation and modern slavery in high-risk sectors.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: GLAA Target entity description: GLAA is a UK government body responsible for licensing labour providers and investigating labour exploitation and modern slavery in high-risk sectors.
-
A.
Gla
Gla is a large fortified Mycenaean archaeological site in Boeotia, Greece, notable for its massive walls and strategic position overlooking the former Lake Kopais.
-
B.
GLA
GLA is the three-letter IATA airport code for Glasgow Airport, the main international airport serving Glasgow, Scotland.
-
C.
Gliz
Gliz is one of the official mascots of the 2006 Winter Olympics in Turin, Italy, depicted as a stylized anthropomorphic ice cube symbolizing winter sports and modernity.
-
D.
GCLA
GCLA is the ICAO airport code for La Palma Airport in Spain’s Canary Islands.
-
E.
Lama glama
Lama glama is the domesticated South American camelid commonly known as the llama, used as a pack animal and for its wool.
- 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_69b34542fd908190b11b08faad8decfd |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35133688c8190ab5527ae01748f13 |
completed | March 12, 2026, 11:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5d09bf304819084fc1b9162c8b48a |
completed | March 14, 2026, 9:18 p.m. |
| NEDg | Description generation | batch_69b5d48a56f881909cc75f45d87c8151 |
completed | March 14, 2026, 9:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5d4f99ff08190957b46cd84954f79 |
completed | March 14, 2026, 9:36 p.m. |
Created at: March 12, 2026, 11:13 p.m.