Triple
T20400614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Mathews |
E500320
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Standing Fast
Standing Fast is a novel by Tom Mathews that explores themes of personal conviction and resilience in the face of social and political upheaval.
|
E1428170
|
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: Standing Fast | Statement: [Tom Mathews, notableWork, Standing Fast]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Standing Fast Context triple: [Tom Mathews, notableWork, Standing Fast]
-
A.
Standing Fast
Standing Fast is the autobiography of civil rights leader Roy Wilkins, chronicling his life and pivotal role in the struggle for racial equality in the United States.
-
B.
Hold Fast
Hold Fast is the traditional battle cry and motto associated with the Scottish Clan MacLeod, symbolizing steadfastness and loyalty.
-
C.
Stand Firm
"Stand Firm" is a reggae track by Peter Tosh featured on his 1978 album *Bush Doctor*.
-
D.
Going Strong
"Going Strong" is a song featured on the soundtrack of the American reality singing competition television series "The Voice."
-
E.
We Stand on Guard
We Stand on Guard is a science fiction comic miniseries that depicts a future war between Canada and the United States, written by Brian K. Vaughan with art by Steve Skroce.
- 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: Standing Fast Triple: [Tom Mathews, notableWork, Standing Fast]
Generated description
Standing Fast is a novel by Tom Mathews that explores themes of personal conviction and resilience in the face of social and political upheaval.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Standing Fast Target entity description: Standing Fast is a novel by Tom Mathews that explores themes of personal conviction and resilience in the face of social and political upheaval.
-
A.
Standing Fast
Standing Fast is the autobiography of civil rights leader Roy Wilkins, chronicling his life and pivotal role in the struggle for racial equality in the United States.
-
B.
Hold Fast
Hold Fast is the traditional battle cry and motto associated with the Scottish Clan MacLeod, symbolizing steadfastness and loyalty.
-
C.
Stand Firm
"Stand Firm" is a reggae track by Peter Tosh featured on his 1978 album *Bush Doctor*.
-
D.
Going Strong
"Going Strong" is a song featured on the soundtrack of the American reality singing competition television series "The Voice."
-
E.
We Stand on Guard
We Stand on Guard is a science fiction comic miniseries that depicts a future war between Canada and the United States, written by Brian K. Vaughan with art by Steve Skroce.
- 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_69e0b4a81bec8190b69adfdc1336a015 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6798db79c819085e3a2526538726f |
completed | April 20, 2026, 7:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08762bd7e881909ceddb1b3c26a914 |
completed | May 16, 2026, 1:50 p.m. |
| NEDg | Description generation | batch_6a0877b7ed888190bccc1ba665528aca |
completed | May 16, 2026, 1:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a087834ea1c8190b1b94c70a807668a |
completed | May 16, 2026, 1:59 p.m. |
Created at: April 16, 2026, 11:29 a.m.