Triple
T23269520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CRESST |
E588248
|
entity |
| Predicate | relatedExperiment |
P37
|
FINISHED |
| Object |
CDMS
CDMS (Cryogenic Dark Matter Search) is a physics experiment designed to directly detect dark matter particles using ultra-cold detectors deep underground.
|
E1577161
|
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: CDMS | Statement: [CRESST, relatedExperiment, CDMS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CDMS Context triple: [CRESST, relatedExperiment, CDMS]
-
A.
CDM
CDM is the commonly used abbreviation for Club Deportivo Mérida, a Spanish football club based in Mérida, Extremadura.
-
B.
CDM
CDM is the College of Management of Technology, an academic unit focused on integrating management, economics, and technology within a university setting.
-
C.
CDM
CDM is the acronym commonly used for DePaul University's College of Computing and Digital Media, which offers programs in technology, design, and media arts.
-
D.
CDM
CDM is a hands-on children’s museum in San Jose, California, known for interactive exhibits that promote learning through play and exploration.
-
E.
CDM
CDM is a United Nations climate policy mechanism under the Kyoto Protocol that allows emission-reduction projects in developing countries to earn tradable carbon credits.
- 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: CDMS Triple: [CRESST, relatedExperiment, CDMS]
Generated description
CDMS (Cryogenic Dark Matter Search) is a physics experiment designed to directly detect dark matter particles using ultra-cold detectors deep underground.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: CDMS Target entity description: CDMS (Cryogenic Dark Matter Search) is a physics experiment designed to directly detect dark matter particles using ultra-cold detectors deep underground.
-
A.
CDM
CDM is the commonly used abbreviation for Club Deportivo Mérida, a Spanish football club based in Mérida, Extremadura.
-
B.
CDM
CDM is the acronym commonly used for DePaul University's College of Computing and Digital Media, which offers programs in technology, design, and media arts.
-
C.
CDM
CDM is the College of Management of Technology, an academic unit focused on integrating management, economics, and technology within a university setting.
-
D.
CDM
CDM is a United Nations climate policy mechanism under the Kyoto Protocol that allows emission-reduction projects in developing countries to earn tradable carbon credits.
-
E.
CDM
CDM is a hands-on children’s museum in San Jose, California, known for interactive exhibits that promote learning through play and exploration.
- 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_69e25d148adc819088efbf42672604e9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1957219188190b30bceffad1542da |
completed | April 29, 2026, 5:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c3f7797a481909c56589d1d3292ea |
completed | May 19, 2026, 10:46 a.m. |
| NEDg | Description generation | batch_6a0c40297d3c8190b366b60cec3dbbf8 |
completed | May 19, 2026, 10:49 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c40ffd67481908931ffc2d91fb02b |
completed | May 19, 2026, 10:52 a.m. |
Created at: April 17, 2026, 4:45 p.m.