Triple
T129445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Columbia University Vagelos College of Physicians and Surgeons |
E2621
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object |
P&S
P&S is the commonly used abbreviation for the Columbia University Vagelos College of Physicians and Surgeons, a leading medical school in New York City.
|
E14691
|
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: P&S | Statement: [Columbia University Vagelos College of Physicians and Surgeons, shortName, P&S]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: P&S Context triple: [Columbia University Vagelos College of Physicians and Surgeons, shortName, P&S]
-
A.
PV
PV is the post-nominal abbreviation used to denote recipients of the Padma Vibhushan, one of India’s highest civilian honors.
-
B.
PS
PS is the two-letter ISO 3166 country code assigned to the State of Palestine, used in international standards and country designation.
-
C.
PK
PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
-
D.
PE
PE is the two-letter ISO 3166-1 alpha-2 country code assigned to Peru for international standardization and referencing.
-
E.
Performa
Performa was a line of consumer-oriented Macintosh personal computers produced by Apple in the 1990s, marketed as affordable, all-in-one home and small-office systems.
- 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: P&S Triple: [Columbia University Vagelos College of Physicians and Surgeons, shortName, P&S]
Generated description
P&S is the commonly used abbreviation for the Columbia University Vagelos College of Physicians and Surgeons, a leading medical school in New York City.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: P&S Target entity description: P&S is the commonly used abbreviation for the Columbia University Vagelos College of Physicians and Surgeons, a leading medical school in New York City.
-
A.
PV
PV is the post-nominal abbreviation used to denote recipients of the Padma Vibhushan, one of India’s highest civilian honors.
-
B.
PS
PS is the two-letter ISO 3166 country code assigned to the State of Palestine, used in international standards and country designation.
-
C.
PK
PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
-
D.
PE
PE is the two-letter ISO 3166-1 alpha-2 country code assigned to Peru for international standardization and referencing.
-
E.
Performa
Performa was a line of consumer-oriented Macintosh personal computers produced by Apple in the 1990s, marketed as affordable, all-in-one home and small-office systems.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a2576518e0819096b35d8af7a4d1bd |
completed | Feb. 28, 2026, 2:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2a3d5c7bc8190ba8b36db41a1a57f |
completed | Feb. 28, 2026, 8:14 a.m. |
| NEDg | Description generation | batch_69a2a4f0e7c081908966789fd07e59a2 |
completed | Feb. 28, 2026, 8:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a2a58757d081908c7c5469c485f1cc |
completed | Feb. 28, 2026, 8:21 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.