Triple
T8431123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ARRAY |
E199115
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object |
AFFRM
AFFRM (African-American Film Festival Releasing Movement) was a distribution collective dedicated to releasing and promoting independent films by and about Black people in the United States.
|
E732707
|
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: AFFRM | Statement: [ARRAY, shortName, AFFRM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AFFRM Context triple: [ARRAY, shortName, AFFRM]
-
A.
AFF
AFF is the ASEAN Football Federation, the regional governing body for football in Southeast Asia under the Asian Football Confederation.
-
B.
AFRM
AFRM is the stock ticker symbol for Affirm Holdings, Inc., a financial technology company known for its buy-now-pay-later payment solutions.
-
C.
AFRF
AFRF is the commonly used English abbreviation for the Russian Armed Forces, the military organization responsible for the defense and security of the Russian Federation.
-
D.
AAF
AAF is the common abbreviation for the Alliance of American Football, a short-lived professional American football league that operated in 2019.
-
E.
AF
AF is a 16-bit register pair in the Zilog Z80 CPU that combines the accumulator (A) and the flags register (F) for arithmetic and logic operations.
- 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: AFFRM Triple: [ARRAY, shortName, AFFRM]
Generated description
AFFRM (African-American Film Festival Releasing Movement) was a distribution collective dedicated to releasing and promoting independent films by and about Black people in the United States.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: AFFRM Target entity description: AFFRM (African-American Film Festival Releasing Movement) was a distribution collective dedicated to releasing and promoting independent films by and about Black people in the United States.
-
A.
AFF
AFF is the ASEAN Football Federation, the regional governing body for football in Southeast Asia under the Asian Football Confederation.
-
B.
AFRM
AFRM is the stock ticker symbol for Affirm Holdings, Inc., a financial technology company known for its buy-now-pay-later payment solutions.
-
C.
AFRF
AFRF is the commonly used English abbreviation for the Russian Armed Forces, the military organization responsible for the defense and security of the Russian Federation.
-
D.
AAF
AAF is the common abbreviation for the Alliance of American Football, a short-lived professional American football league that operated in 2019.
-
E.
AF
AF is the two-letter IATA airline designator assigned to Air France, the flag carrier of France.
- 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_69ca8313c99081909a5c6d83b91de5b3 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbd1a4876c81908d5a708bb1f35683 |
completed | March 31, 2026, 1:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce0380ed948190bdba247d67769ade |
completed | April 2, 2026, 5:49 a.m. |
| NEDg | Description generation | batch_69ce07851c4081909a9468a386035bb2 |
completed | April 2, 2026, 6:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce07ec00248190bb10fee54265c7f9 |
completed | April 2, 2026, 6:08 a.m. |
Created at: March 30, 2026, 6:07 p.m.