Triple
T3535185
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Towers Watson |
E74753
|
entity |
| Predicate | tickerSymbol |
P1447
|
FINISHED |
| Object |
TW
TW is the stock ticker symbol for Towers Watson, a global professional services firm specializing in risk management, insurance brokerage, and human resources consulting.
|
E367686
|
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: TW | Statement: [Towers Watson, tickerSymbol, TW]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TW Context triple: [Towers Watson, tickerSymbol, TW]
-
A.
TW
TW is the two-letter ISO 3166 country code assigned to Taiwan (commonly referred to as Chinese Taipei in certain international contexts).
-
B.
TW
TW is a UK postcode area in southwest London and parts of Surrey, covering towns such as Twickenham and Staines-upon-Thames.
-
C.
TR
TR is the two-letter ISO 3166-1 alpha-2 country code assigned to Turkey for international standardization and referencing.
-
D.
TOR
TOR is the standard three-letter abbreviation used to represent the Toronto Maple Leafs in sports standings, statistics, and media.
-
E.
TOR
TOR is the official code designation used for the Georgian football club FC Torpedo Kutaisi.
- 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: TW Triple: [Towers Watson, tickerSymbol, TW]
Generated description
TW is the stock ticker symbol for Towers Watson, a global professional services firm specializing in risk management, insurance brokerage, and human resources consulting.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: TW Target entity description: TW is the stock ticker symbol for Towers Watson, a global professional services firm specializing in risk management, insurance brokerage, and human resources consulting.
-
A.
TW
TW is the two-letter ISO 3166 country code assigned to Taiwan (commonly referred to as Chinese Taipei in certain international contexts).
-
B.
TW
TW is a UK postcode area in southwest London and parts of Surrey, covering towns such as Twickenham and Staines-upon-Thames.
-
C.
TR
TR is the two-letter ISO 3166-1 alpha-2 country code assigned to Turkey for international standardization and referencing.
-
D.
TOR
TOR is the standard three-letter abbreviation used to represent the Toronto Maple Leafs in sports standings, statistics, and media.
-
E.
TOR
TOR is the official code designation used for the Georgian football club FC Torpedo Kutaisi.
- 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_69ad85d1a3948190931fd1ea1f49717b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbcc4c1d081908938efb71938e1a3 |
completed | March 8, 2026, 6:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b38bcf7ffc81909242cf67f5aa7b3d |
completed | March 13, 2026, 4 a.m. |
| NEDg | Description generation | batch_69b38d8287408190933884c2b7bff312 |
completed | March 13, 2026, 4:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b38ddfce348190b5a7d9abdb7a6826 |
completed | March 13, 2026, 4:09 a.m. |
Created at: March 8, 2026, 3:19 p.m.