Triple
T9741367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Foursquare |
E236192
|
entity |
| Predicate | acquired |
P2511
|
FINISHED |
| Object |
Factual
Factual was a location data company known for providing global places and movement data used in advertising, mobile apps, and analytics.
|
E818828
|
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: Factual | Statement: [Foursquare, acquired, Factual]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Factual Context triple: [Foursquare, acquired, Factual]
-
A.
FACT
FACT is the ICAO airport code assigned to Cape Town International Airport in South Africa.
-
B.
True
"True" is a 1983 soft rock ballad by British band Spandau Ballet, widely recognized as their signature hit and a classic of the New Romantic era.
-
C.
True
"True" is a song featured on the album "Human" by the British singer and songwriter Rag'n'Bone Man.
-
D.
Facts and Propositions
Facts and Propositions is a 1927 philosophical work by F. P. Ramsey that develops an influential account of truth, belief, and the nature of propositions within analytic philosophy.
-
E.
Facta Non Verba
Facta Non Verba is the Latin motto of Canada's elite special operations unit Joint Task Force 2, emphasizing action over words.
- 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: Factual Triple: [Foursquare, acquired, Factual]
Generated description
Factual was a location data company known for providing global places and movement data used in advertising, mobile apps, and analytics.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Factual Target entity description: Factual was a location data company known for providing global places and movement data used in advertising, mobile apps, and analytics.
-
A.
FACT
FACT is the ICAO airport code assigned to Cape Town International Airport in South Africa.
-
B.
True
"True" is a 1983 soft rock ballad by British band Spandau Ballet, widely recognized as their signature hit and a classic of the New Romantic era.
-
C.
True
"True" is a song featured on the album "Human" by the British singer and songwriter Rag'n'Bone Man.
-
D.
Facts and Propositions
Facts and Propositions is a 1927 philosophical work by F. P. Ramsey that develops an influential account of truth, belief, and the nature of propositions within analytic philosophy.
-
E.
Facta Non Verba
Facta Non Verba is the Latin motto of Canada's elite special operations unit Joint Task Force 2, emphasizing action over words.
- 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_69ca84d3e24481908a476e2231123cf9 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9f2af3e48190b83a442cd0e84062 |
completed | April 1, 2026, 10:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1aff2339c8190b164b13b54a40cec |
completed | April 5, 2026, 12:42 a.m. |
| NEDg | Description generation | batch_69d1b08ba1f48190830852f9d60e3368 |
completed | April 5, 2026, 12:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1b124659481909e7a2ecaf01d8a50 |
completed | April 5, 2026, 12:47 a.m. |
Created at: March 30, 2026, 8:23 p.m.